Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize fixed reasoning patterns. Furthermore, jointly training for reasoning and segmentation can compromise pixel-level precision. To address these issues, we introduce AURORA, a novel framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation. We employ a structured Chain-of-Thought (CoT) prompting mechanism to guide the model through a step-by-step reasoning process and introduce a novel segmentation feature distillation loss to effectively integrate these reasoning abilities without sacrificing segmentation performance. To further cultivate the model's genuine reasoning capabilities, we devise a further two-stage training strategy: first, a ``corrective reflective-style training" stage utilizes self-correction to enhance the quality of reasoning paths, followed by reinforcement learning via Group Reward Policy Optimization (GRPO) to bolster robustness in challenging scenarios. Experiments demonstrate that AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.

Few-shot semantic segmentation (FSS) often struggles with the intra-class diversity issue between query and support images, caused by the category-biased information provided by limited annotated support images for matching objects. While increasing the number of annotated support images could mitigate this bias, it is impractical within the few-shot learning framework. Therefore, our proposed Unlabeled Query Integration Few-Shot Segmentation (UQI-FSS) tackles this challenge by incorporating unlabeled query images into the learning paradigm. This approach aims to achieve a more comprehensive category representation, which is essential to enhance segmentation accuracy in various scenarios. However, integrating unlabeled query images directly requires careful management to prevent the dilution of vital information from the annotated support set. To address this issue, we present an Unlabeled Query Integration Network (UQINet), which adaptively extracts beneficial and suppresses detrimental information from the unlabeled query images. Specifically, we first introduce an Information Bridging Module to close the gap between support and unlabeled query features, generating a pseudo-support set enriched with additional category data. Next, we introduce a Query Fusion Module to incorporate query information from both prototype and pixel levels into the pseudo-support features, thus improving their adaptability to the query. Finally, we propose an Adaptive Selection Module to select effective category information and combine the pseudo-support features, thereby activating target objects for precise segmentation prediction. Experimental results show considerable performance improvements over previous methods on various FSS benchmarks. The application of this method to four challenging scenarios further underscores its versatility and practical value.

Salient object detection (SOD) and camouflaged object detection (COD) are related but distinct binary mapping tasks, each involving multiple modalities that share commonalities while maintaining unique characteristics. Existing approaches often rely on complex, task-specific architectures, leading to redundancy and limited generalization. Our previous work, VSCode, introduced a generalist model that effectively handles four SOD tasks and two COD tasks. VSCode leveraged VST as its foundation model and incorporated 2D prompts within an encoder-decoder framework to capture domain and task-specific knowledge, utilizing a prompt discrimination loss to optimize the model. Building upon the proven effectiveness of our previous work VSCode, we identify opportunities to further strengthen generalization capabilities through focused modifications in model design and optimization strategy. To unlock this potential, we propose VSCode-v2, an extension that introduces a Mixture of Prompt Experts (MoPE) layer to generate adaptive prompts. We also redesign the training process into a two-stage approach: first learning shared features across tasks, then capturing specific characteristics. To preserve knowledge during this process, we incorporate distillation from our conference version model. Furthermore, we propose a contrastive learning mechanism with data augmentation to strengthen the relationships between prompts and feature representations. VSCode-v2 demonstrates balanced performance improvements across six SOD and COD tasks. Moreover, VSCode-v2 effectively handles various multimodal inputs and exhibits zero-shot generalization capability to novel tasks, such as RGB-D Video SOD.

Previous methods often utilize CLIP semantic classifiers with class names for zero-shot object counting. However, they ignore crucial density and depth knowledge for counting tasks. Thus, we propose a density-aware and depth-aware prompt counting model, which captures density information via learning density-aware prompts based on density-aware contrastive loss and incorporates depth guidance with predefined depth-aware prompts. To facilitate the training process, we design two strategies for standard counting loss and the contrastive loss, where the former prioritizes larger and sparser objects initially, gradually focusing on smaller and denser objects, and the latter adopts coarse-to-fine density learning. Besides, we construct a dataset named LVIS-372 with more real-world scenarios and balanced instance distribution compared to existing ones. Finally, the experimental results demonstrate the effectiveness of our proposed method.

Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains and the limited availability of support data. Most CD-FSS methods redesign and retrain in-domain FSS models using abundant base data from the source domain, which are effective but costly to train. To address these issues, we propose adapting informative model structures of the well-trained FSS model for target domains by learning domain characteristics from few-shot labeled support samples during inference, thereby eliminating the need for source domain retraining. Specifically, we first adaptively identify domain-specific model structures by measuring parameter importance using a novel structure Fisher score in a data-dependent manner. Then, we progressively train the selected informative model structures with hierarchically constructed training samples, progressing from fewer to more support shots. The resulting Informative Structure Adaptation (ISA) method effectively addresses domain shifts and equips existing well-trained in-domain FSS models with flexible adaptation capabilities for new domains, eliminating the need to redesign or retrain CD-FSS models on base data. Extensive experiments validate the effectiveness of our method, demonstrating superior performance across multiple CD-FSS benchmarks. Codes are at https://github.com/fanq15/ISA.

Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.

General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based large-scale affordance prediction data, leading to considerable concern about open-world effectiveness. To address this limitation, we build a large-scale grasping-oriented affordance segmentation benchmark with human-like instructions, named RAGNet. It contains 273k images, 180 categories, and 26k reasoning instructions. The images cover diverse embodied data domains, such as wild, robot, ego-centric, and even simulation data. They are carefully annotated with an affordance map, while the difficulty of language instructions is largely increased by removing their category name and only providing functional descriptions. Furthermore, we propose a comprehensive affordance-based grasping framework, named AffordanceNet, which consists of a VLM pre-trained on our massive affordance data and a grasping network that conditions an affordance map to grasp the target. Extensive experiments on affordance segmentation benchmarks and real-robot manipulation tasks show that our model has a powerful open-world generalization ability. Our data and code is available at https://github.com/wudongming97/AffordanceNet.

Most existing CoSOD models focus solely on extracting co-saliency cues while neglecting explicit exploration of background regions, potentially leading to difficulties in handling interference from complex background areas. To address this, this paper proposes a Discriminative co-saliency and background Mining Transformer framework (DMT) to explicitly mine both co-saliency and background information and effectively model their discriminability. DMT first learns two types of tokens by disjointly extracting co-saliency and background information from segmentation features, then performs discriminability within the segmentation features guided by these well-learned tokens. In the first phase, we propose economic multi-grained correlation modules for efficient detection information extraction, including Region-to-Region (R2R), Contrast-induced Pixel-to-Token (CtP2T), and Co-saliency Token-to-Token (CoT2T) correlation modules. In the subsequent phase, we introduce Token-Guided Feature Refinement (TGFR) modules to enhance discriminability within the segmentation features. To further enhance the discriminative modeling and practicality of DMT, we first upgrade the original TGFR's intra-image modeling approach to an intra-group one, thus proposing Group TGFR (G-TGFR), which is more suitable for the co-saliency task. Subsequently, we designed a Noise Propagation Suppression (NPS) mechanism to apply our model to a more practical open-world scenario, ultimately presenting our extended version, i.e. DMT+O. Extensive experimental results on both conventional CoSOD and open-world CoSOD benchmark datasets demonstrate the effectiveness of our proposed model.

Few-shot segmentation (FSS) aims to accurately segment target objects in a query image using only a limited number of annotated support images. Existing approaches typically follow a paradigm that directly leverages category information from the support set to identify target objects in the query. However, these methods often ignore the category information gap between query and support images, leading to suboptimal performance when faced with images containing objects exhibiting significant intra-class diversity. To address this issue, we propose a novel framework that introduces intermediate prototypes to capture both deterministic information from the support images and adaptive knowledge from the query at multiple scales. Our framework, named the K-shot Multi-scale Intermediate Prototype Mining Transformer (KMIPMT), is based on the Transformer architecture and learns intermediate prototypes in an iterative manner, where each KMIPMT layer propagates category information from both K-shot support features and multi-scale query features to intermediate prototypes. This information is then utilized to activate the query feature map. Through repeated iterations, both intermediate prototypes and the query feature are progressively enhanced, and the final refined query feature is used for generating precise segmentation predictions. Despite its simplicity, our method achieves remarkable performance gains on standard benchmarks, including PASCAL-$5^{i}$5i, COCO-$20^{i}$20i, and FSS-1000, setting new state-of-the-art results. Furthermore, we explore several practical and challenging extensions of our method, including 3D point cloud FSS, zero-shot segmentation, weak-label FSS, and cross-domain FSS. These extensions showcase the versatility and effectiveness of our proposed KMIPMT framework across different domains and scenarios.

In recent times, following the paradigm of DETR (DEtection TRansformer), query-based end-to-end instance segmentation (QEIS) methods have exhibited superior performance compared to CNN-based models, particularly when trained on large-scale datasets. Nevertheless, the effectiveness of these QEIS methods diminishes significantly when confronted with limited training data. This limitation arises from their reliance on substantial data volumes to effectively train the pivotal queries/kernels that are essential for acquiring localization and shape priors. To address this problem, we propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts (UPLVP), which improves QEIS models' instance segmentation by bringing language-vision prompts to queries/kernels. Our method consists of three parts: (1) Masks Proposal: Utilizes language-vision models to generate pseudo masks based on unlabeled images. (2) Prompt-Kernel Matching: Converts pseudo masks into prompts and injects the best-matched localization and shape features to their corresponding kernels. (3) Kernel Supervision: Formulates supervision for pre-training at the kernel level to ensure robust learning. With the help of our pre-training method, QEIS models can converge faster and perform better than CNN-based models in low-data regimes. Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models' performance can be significantly improved when pre-trained with our method.

Few-shot semantic segmentation (FSS) aims to segment the target object under the condition of a few annotated samples. However, current studies on FSS primarily concentrate on extracting information related to the object, resulting in inadequate identification of ambiguous regions, particularly in non-target areas, including the background (BG) and Distracting Objects (DOs). Intuitively, to alleviate this problem, we propose a novel framework, namely NTRENet++, to explicitly mine and eliminate BG and DO regions in the query. First, we introduce a BG Mining Module (BGMM) to extract BG information and generate a comprehensive BG prototype from all images. For this purpose, a BG mining loss is formulated to supervise the learning of BGMM, utilizing only the known target object segmentation ground truth. Subsequently, based on this BG prototype, we employ a BG Eliminating Module to filter out the BG information from the query and obtain a BG-free result. Following this, the target information is utilized in the target matching module to generate the initial segmentation result. Finally, a DO Eliminating Module is proposed to further mine and eliminate DO regions, based on which we can obtain a BG and DO-free target object segmentation result. Moreover, we present a prototypical-pixel contrastive learning algorithm to enhance the model’s capability to differentiate the target object from DOs. Extensive experiments conducted on both PASCAL-5i and COCO-20i datasets demonstrate the effectiveness of our approach despite its simplicity. Additionally, we extend our method to the few-shot video object segmentation task and achieve improved performance on a baseline model, demonstrating its generalization ability. Code is available athttps://github.com/LIUYUANWEI98/NTRENet++.

RGB-D salient object detection (SOD) has gained tremendous attention in recent years. In particular, transformer has been employed and shown great potential. However, existing transformer models usually overlook the vital edge information, which is a major issue restricting the further improvement of SOD accuracy. To this end, we propose a novel edge-aware RGB-D SOD transformer, called EM-Trans, which explicitly models the edge information in a dual-band decomposition framework. Specifically, we employ two parallel decoder networks to learn the high-frequency edge and low-frequency body features from the low- and high-level features extracted from a two-steam multimodal backbone network, respectively. Next, we propose a cross-attention complementarity exploration module to enrich the edge/body features by exploiting the multimodal complementarity information. The refined features are then fed into our proposed color-hint guided fusion module for enhancing the depth feature and fusing the multimodal features. Finally, the resulting features are fused using our deeply supervised progressive fusion module, which progressively integrates edge and body features for predicting saliency maps. Our model explicitly considers the edge information for accurate RGB-D SOD, overcoming the limitations of existing methods and effectively improving the performance. Extensive experiments on benchmark datasets demonstrate that EM-Trans is an effective RGB-D SOD framework that outperforms the current state-of-the-art models, both quantitatively and qualitatively. A further extension to RGB-T SOD demonstrates the promising potential of our model in various kinds of multimodal SOD tasks.

Gaze object prediction aims to predict the location and category of the object that is watched by a human. Previous gaze object prediction works use CNN-based object detectors to predict the object's location. However, we find that Transformer-based object detectors can predict more accurate object location for dense objects in retail scenarios. Moreover, the long-distance modeling capability of the Transformer can help to build relationships between the human head and the gaze object, which is important for the GOP task. To this end, this paper introduces Transformer into the fields of gaze object prediction and proposes an end-to-end Transformer-based gaze object prediction method named TransGOP. Specifically, TransGOP uses an off-the-shelf Transformer-based object detector to detect the location of objects and designs a Transformer-based gaze autoencoder in the gaze regressor to establish long-distance gaze relationships. Moreover, to improve gaze heatmap regression, we propose an object-to-gaze cross-attention mechanism to let the queries of the gaze autoencoder learn the global-memory position knowledge from the object detector. Finally, to make the whole framework end-to-end trained, we propose a Gaze Box loss to jointly optimize the object detector and gaze regressor by enhancing the gaze heatmap energy in the box of the gaze object. Extensive experiments on the GOO-Synth and GOO-Real datasets demonstrate that our TransGOP achieves state-of-the-art performance on all tracks, i.e., object detection, gaze estimation, and gaze object prediction. Our code will be available at https://github.com/chenxi-Guo/TransGOP.git.

Applying Neural Radiance Fields (NeRF) to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, i.e., the “label rendering” task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, as shown in Fig. 1 we conduct experimental comparisons under two perception tasks (i.e. semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94%,11.76%, and 8.47% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively. Project.

Salient object detection (SOD) and camouflaged object detection (COD) are related yet distinct binary mapping tasks. These tasks involve multiple modalities, sharing commonalities and unique cues. Existing research often employs intricate task-specific specialist models, potentially leading to redundancy and suboptimal results. We introduce VS-Code, a generalist model with novel 2D prompt learning, to jointly address four SOD tasks and three COD tasks. We utilize VST as the foundation model and introduce 2D prompts within the encoder-decoder architecture to learn domain and task-specific knowledge on two separate dimensions. A prompt discrimination loss helps disentangle peculiarities to benefit model optimization. VSCode outperforms state-of-the-art methods across six tasks on 26 datasets and exhibits zero-shot generalization to unseen tasks by combining 2D prompts, such as RGB-D COD. Source code has been available at https://github.com/Sssssuperior/VSCode.

Existing few-shot semantic segmentation methods typically rely on a one-way flow of category information from support to query, ignoring the impact of intra-class diversity. To address this, drawing inspiration from cybernetics, we introduce a Query Feedback Branch (QFB) to propagate query information back to support, generating a query-related support prototype that is more aligned with the query. Subsequently, a Query Amplifier Branch (QAB) is employed to amplify target objects in the query using the acquired support prototype. To further improve the model, we propose a Query Rectification Module (QRM), which utilizes the prediction disparity in the query before and after support activation to identify challenging positive and negative samples from ambiguous regions for query self-rectification. Furthermore, we integrate the QFB, QAB, and QRM into a feedback and rectification layer and incorporate it into an iterative pipeline. This configuration enables the progressive enhancement of bidirectional reciprocative flow of category information between query and support, effectively providing query-adaptive support information and addressing the intra-class diversity problem. Extensive experiments conducted on both PASCAL-5i and COCO-20i datasets validate the effectiveness of our approach. The code is available at https://github.com/LIUYUANWEI98/IFRNet .

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size. Therefore, we propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources. Specifically, we first propose an input spatial representation distillation (ISRD) mechanism to transfer spatial knowledge from large images to student's input module, which can facilitate stable knowledge transfer between CNN and ViT. Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge. Finally, we adapt pixel distillation to object detection via an aligned feature for preservation (AFP) strategy for TAS, which aligns output dimensions of detectors at each stage by manipulating features and anchors of the assistant. Comprehensive experiments on image classification and object detection demonstrate the effectiveness of our method.

This paper proposes a scribble-based weakly supervised RGB-D salient object detection (SOD) method to relieve the annotation burden from pixel-wise annotations. In view of the ensuing performance drop, we summarize two natural deficiencies of the scribbles and try to alleviate them, which are the weak richness of the pixel training samples (WRPS) and the poor structural integrity of the salient objects (PSIO). WRPS hinders robust saliency perception learning, which can be alleviated via model design for robust feature learning and pseudo labels generation for training sample enrichment. Specifically, we first design a dynamic searching process module as a meta operation to conduct multi-scale and multi-modal feature fusion for the robust RGB-D SOD model construction. Then, a dual-branch consistency learning mechanism is proposed to generate enough pixel training samples for robust saliency perception learning. PSIO makes direct structural learning infeasible since scribbles can not provide integral structural supervision. Thus, we propose an edge-region structure-refinement loss to recover the structural information and make precise segmentation. We deploy all components and conduct ablation studies on two baselines to validate their effectiveness and generalizability. Experimental results on eight datasets show that our method outperforms other scribble-based SOD models and achieves comparable performance with fully supervised state-of-the-art methods.

While previous CNN-based models have exhibited promising results for salient object detection (SOD), their ability to explore global long-range dependencies is restricted. Our previous work, the Visual Saliency Transformer (VST), addressed this constraint from a transformer-based sequence-to-sequence perspective, to unify RGB and RGB-D SOD. In VST, we developed a multi-task transformer decoder that concurrently predicts saliency and boundary outcomes in a pure transformer architecture. Moreover, we introduced a novel token upsampling method called reverse T2T for predicting a high-resolution saliency map effortlessly within transformer-based structures. Building upon the VST model, we further propose an efficient and stronger VST version in this work,i.e.VST++. To mitigate the computational costs of the VST model, we propose a Select-Integrate Attention (SIA) module, partitioning foreground into fine-grained segments and aggregating background information into a single coarse-grained token. To incorporate 3D depth information with low cost, we design a novel depth position encoding method tailored for depth maps. Furthermore, we introduce a token-supervised prediction loss to provide straightforward guidance for the task-related tokens. We evaluate our VST++model across various transformer-based backbones on RGB, RGB-D, and RGB-T SOD benchmark datasets. Experimental results show that our model outperforms existing methods while achieving a 25% reduction in computational costs without significant performance compromise. The demonstrated strong ability for generalization, enhanced performance, and heightened efficiency of our VST++model highlight its potential.

When given a group of relevant images for co-salient object detection (Co-SOD), humans first summarize consensus cues from the whole group and then search for co-salient objects in each image. Most previous methods do not consider robustness, scalability, or stability in the summarization stage and adopt a simple fusion strategy to fuse consensus and image features in the searching stage. Our work presents a novel consensus-aware dynamic convolution (CADC) model directly from the “summarize and search” perspective to explicitly and effectively perform Co-SOD. For the summarization stage, we extract robust individual image features by a pooling method and integrate them to generate consensus features via self-attention, thus modeling the scalability and stability. Then, we simultaneously learn two types of consensus-aware dynamic kernels, i.e., a common kernel to capture group-wise common knowledge and adaptive kernels to mine image-specific consensus cues. For the second stage, we adopt dynamic convolution to perform object searching. A novel data synthesis strategy is also developed for model training. Although CADC has obtained competitive performance, we argue that incrementally learning dynamic kernels and representations is more intuitive and natural instead of using a simultaneous scheme, thus presenting our CADC++, an extension of CADC. Concretely, we first adopt the common kernel based dynamic convolution to capture coarse common cues as priors and then use the adaptive kernel based dynamic convolution for mining image-specific details. We also propose a recursive guidance strategy to further explore deep interactions among the two kinds of kernels and image features. Besides, we annotate several challenging attributes for Co-SOD datasets and perform attribute-based evaluation and robustness analysis to promote thorough model evaluation for the Co-SOD field. Extensive experimental results on four benchmark datasets verify both the effectiveness and robustness of our proposed method.

In this study, we propose a novel approach for RGB-D salient instance segmentation using a dual-branch cross-modal feature calibration architecture called CalibNet. Our method simultaneously calibrates depth and RGB features in the kernel and mask branches to generate instance-aware kernels and mask features. CalibNet consists of three simple modules, a dynamic interactive kernel (DIK) and a weight-sharing fusion (WSF), which work together to generate effective instance-aware kernels and integrate cross-modal features. To improve the quality of depth features, we incorporate a depth similarity assessment (DSA) module prior to DIK and WSF. In addition, we further contribute a new DSIS dataset, which contains 1,940 images with elaborate instance-level annotations. Extensive experiments on three challenging benchmarks show that CalibNet yields a promising result, i.e., 58.0% AP with 320×480 input size on the COME15K-E test set, which significantly surpasses the alternative frameworks. Our code and dataset will be publicly available at: https://github.com/PJLallen/CalibNet.

Many multi-view camera-based 3D object detection models transform the image features into Bird’s-Eye-View (BEV) via the Lift-Splat-Shoot (LSS) mechanism, which “lifts” 2D camera-view features to the 3D voxel space based on the predicted depth distribution and then “splats” 3D features into a BEV plane for subsequent 3D object detection. However, the BEV feature in such a one-stage view transformation scheme heavily relies on the quality of the predicted depth distribution and 2D camera-view features, which further determines the final detection performance. In this paper, we propose a BEVRefiner model which performs dual refinement for both depth prediction and 2D camera-view features. On the one hand, we perform light-weight depth refinement in the depth distribution frustum space by incorporating 3D context and depth distribution prior. On the other hand, we reproject the BEV feature back to each camera view to enhance 2D image features. In this way, the original camera-view features can be enhanced by implicitly incorporating 3D contexts and multi-view contexts, which cannot be achieved in the original 2D camera view. We also propose to use dominant depth bins only for the reprojection to save computational burden. Finally, we generate the refined BEV feature using the refined depth distribution and camera-view features for more accurate 3D object detection. Our BEVRefiner can be plugged into LSS-based BEV detectors and we perform extensive experiments on the representative model BEVDet, which strongly verified the efficiency of our proposed approach under several settings.

Besides combining appearance and motion information, another crucial factor for video salient object detection (VSOD) is to mine spatial-temporal (ST) knowledge, including complementary long-short temporal cues and global-local spatial context from neighboring frames. However, the existing methods only explored part of them and ignored their complementarity. In this article, we propose a novel complementary ST transformer (CoSTFormer) for VSOD, which has a short-global branch and a long-local branch to aggregate complementary ST contexts. The former integrates the global context from the neighboring two frames using dense pairwise attention, while the latter is designed to fuse long-term temporal information from more consecutive frames with local attention windows. In this way, we decompose the ST context into a short-global part and a long-local part and leverage the powerful transformer to model the context relationship and learn their complementarity. To solve the contradiction between local window attention and object motion, we propose a novel flow-guided window attention (FGWA) mechanism to align the attention windows with object and camera movements. Furthermore, we deploy CoSTFormer on fused appearance and motion features, thus enabling the effective combination of all three VSOD factors. Besides, we present a pseudo video generation method to synthesize sufficient video clips from static images for training ST saliency models. Extensive experiments have verified the effectiveness of our method and illustrated that we achieve new state-of-the-art results on several benchmark datasets.

Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. We also design a token-guided feature refinement module to enhance the discriminability of the segmentation features under the guidance of the learned tokens. We perform iterative mutual promotion for the segmentation feature extraction and token construction. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method. The source code is available at: https://github.com/dragonlee258079/DMT.

Inspired by DETR variants, query-based end-to-end instance segmentation (QEIS) methods have recently outperformed CNN-based models on large-scale datasets. Yet they would lose efficacy when only a small amount of training data is available since it's hard for the crucial queries/kernels to learn localization and shape priors. To this end, this work offers a novel unsupervised pre-training solution for low-data regimes. Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels. Our method contains three parts: 1) Saliency Masks Proposal is responsible for generating pseudo masks from unlabeled images based on the saliency mechanism. 2) Prompt-Kernel Matching transfers pseudo masks into prompts and injects the corresponding localization and shape priors to the best-matched kernels. 3) Kernel Supervision is applied to supply supervision at the kernel level for robust learning. From a practical perspective, our pre-training method helps QEIS models achieve a similar convergence speed and comparable performance with CNN-based models in low-data regimes. Experimental results show that our method significantly boosts several QEIS models on three datasets.11Code: https://github.com/lifuguan/saliency.prompt

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. However, the performance of the global model is often hampered by non-i.i.d. distribution among the clients, requiring extensive efforts to mitigate inter-client data heterogeneity. Going beyond inter-client data heterogeneity, we note that intra-client heterogeneity can also be observed on complex real-world data and seriously deteriorate FL performance. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Instead of huge instance-adaptive models, we resort to a parameter-efficient fine-tuning method, i.e., scale and shift deep features (SSF), upon a pre-trained model. Specifically, we first train an SSF pool for each client, and aggregate these SSF pools on the server side, thus still maintaining a low communication cost. To enable instance-adaptive inference, for a given instance, we dynamically find the best-matched SSF subsets from the pool and aggregate them to generate an adaptive SSF specified for the instance, thereby reducing the intra-client as well as the inter-client heterogeneity. Extensive experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.

Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art few-shot image segmentation method that combines external support guidance information with adaptive query guidance cues, we propose to leverage multi-grained temporal guidance information for handling the temporal correlation nature of video data. We decompose the query video information into a clip prototype and a memory prototype for capturing local and long-term internal temporal guidance, respectively. Frame prototypes are further used for each frame independently to handle fine-grained adaptive guidance and enable bidirectional clip-frame prototype communication. To reduce the influence of noisy memory, we propose to leverage the structural similarity relation among different predicted regions and the support for selecting reliable memory frames. Furthermore, a new segmentation loss is also proposed to enhance the category discriminability of the learned prototypes. Experimental results demonstrate that our proposed video IPMT model significantly outperforms previous models on two benchmark datasets. Code is available at https://github.com/nankepan/VIPMT.

Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves ∼ 10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets. Codes and results are available at: https://github.com/mczhuge/ICON.

Occlusion is a challenging yet commonly seen problem for facial perception. Existing works resort to deep learning models and perform model training on synthesized data due to the lack of paired real-world data. As a result,they usually perform unsatisfactorily on real-world occluded faces because of domain gaps. In this paper, we decompose the face de-occlusion task into three stages, i.e., occlusion detection, face parsing, and face reconstruction, to alleviate this issue. We first perform occlusion detection and use its results as guidance for the second stage to conduct occlusion-free face parsing. As such, face de-occlusion is first performed on the face paring space with less difficulty. We can train these two stages on both synthesized and real-world images, hence can obtain accurate results for the latter. In the last stage, we use the domain-agnostic occlusion detection map and the face parsing map as the guidance to conduct face reconstruction, thus can reduce the impact of appearance information and improve the model performance on real-world data. Aiming at improving the model capacity of inferring occluded facial appearance, we also propose two types of reference modules to use relevant facial parts to enhance the reconstruction of occluded regions. Consequently, our proposed model achieves promising face de-occlusion results on real-world images.

Existing studies in few-shot semantic segmentation only focus on mining the target object information, however, often are hard to tell ambiguous regions, especially in non-target regions, which include background (BG) and Distracting Objects (DOs). To alleviate this problem, we propose a novel framework, namely Non-Target Region Eliminating (NTRE) network, to explicitly mine and eliminate BG and DO regions in the query. First, a BG Mining Module (BGMM) is proposed to extract the BG region via learning a general BG prototype. To this end, we design a BG loss to supervise the learning of BGMM only using the known target object segmentation ground truth. Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result. Furthermore, we propose a prototypical contrastive learning algorithm to improve the model ability of distinguishing the target object from DOs. Extensive experiments on both PASCAL-5iand COCO-20idatasets show that our approach is effective despite its simplicity. Code is available at https://github.com/LIUYUANWEI98/NERTNet

Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective category information from the support to match with the corresponding objects in query. However, they all ignored the category information gap between query and support images. If the objects in them show large intra-class diversity, forcibly migrating the category information from the support to the query is ineffective. To solve this problem, we are the first to introduce an intermediate prototype for mining both deterministic category information from the support and adaptive category knowledge from the query. Specifically, we design an Intermediate Prototype Mining Transformer (IPMT) to learn the prototype in an iterative way. In each IPMT layer, we propagate the object information in both support and query features to the prototype and then use it to activate the query feature map. By conducting this process iteratively, both the intermediate prototype and the query feature can be progressively improved. At last, the final query feature is used to yield precise segmentation prediction. Extensive experiments on both PASCAL-5i and COCO-20i datasets clearly verify the effectiveness of our IPMT and show that it outperforms previous state-of-the-art methods by a large margin. Code is available at https://github.com/LIUYUANWEI98/IPMT

Conventional salient object detection models cannot differentiate the importance of different salient objects. Recently, two works have been proposed to detect saliency ranking by assigning different degrees of saliency to different objects. However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference. In this paper, we investigate a practical problem setting that requires simultaneously segment salient instances and infer their relative saliency rank order. We present a novel unified model as the first end-to-end solution, where an improved Mask R-CNN is first used to segment salient instances and a saliency ranking branch is then added to infer the relative saliency. For relative saliency ranking, we build a new graph reasoning module by combining four graphs to incorporate the instance interaction relation, local contrast, global contrast, and a high-level semantic prior, respectively. A novel loss function is also proposed to effectively train the saliency ranking branch. Besides, a new dataset and an evaluation metric are proposed for this task, aiming at pushing forward this field of research. Finally, experimental results demonstrate that our proposed model is more effective than previous methods. We also show an example of its practical usage on adaptive image retargeting.

How to effectively fuse cross-modal information is a key problem for RGB-D salient object detection. Early fusion and result fusion schemes fuse RGB and depth information at the input and output stages, respectively, and hence incur distribution gaps or information loss. Many models instead employ a feature fusion strategy, but they are limited by their use of low-order point-to-point fusion methods. In this paper, we propose a novel mutual attention model by fusing attention and context from different modalities. We use the non-local attention of one modality to propagate long-range contextual dependencies for the other, thus leveraging complementary attention cues to achieve high-order and trilinear cross-modal interaction. We also propose to induce contrast inference from the mutual attention and obtain a unified model. Considering that low-quality depth data may be detrimental to model performance, we further propose a selective attention to reweight the added depth cues. We embed the proposed modules in a two-stream CNN for RGB-D SOD. Experimental results demonstrate the effectiveness of our proposed model. Moreover, we also construct a new and challenging large-scale RGB-D SOD dataset of high-quality, which can promote both the training and evaluation of deep models.

Recently, the Part-Object Relational (POR) saliency underpinned by the Capsule Network (CapsNet) has been demonstrated to be an effective modeling mechanism to improve the saliency detection accuracy. However, it is widely known that the current capsule routing operations have huge computational complexity, which seriously limited the usability of the POR saliency models in real-time applications. To this end, this paper takes an early step towards a fast POR saliency inference by proposing a novel disentangled part-object relational network. Concretely, we disentangle horizontal routing and vertical routing from the original omnidirectional capsule routing, thus generating Disentangled Capsule Routing (DCR). This mechanism enjoys two advantages. On one hand, DCR that disentangles orthogonal 1D (i.e., vertical and horizontal) routing greatly reduces parameters and routing complexity, resulting in much faster inference than omnidirectional 2D routing adopted by existing CapsNets. On the other hand, thanks to the light POR cues explored by DCR, we could conveniently integrate the part-object routing process to different feature layers in CNN, rather than just applying it to the small-scaled one as in previous works. This helps to increase saliency inference accuracy. Compared to previous POR saliency detectors, DPORTNet infers visual saliency (5 ∼ 9 ) × faster, and is more accurate. DPORTNet is available under the open-source license at https://github.com/liuyi1989/DCR.

RGB-D co-salient object detection aims to segment co-occurring salient objects when given a group of relevant images and depth maps. Previous methods often adopt separate pipeline and use hand-crafted features, being hard to capture the patterns of co-occurring salient objects and leading to unsatisfactory results. Using end-to-end CNN models is a straightforward idea, but they are less effective in exploiting global cues due to the intrinsic limitation. Thus, in this paper, we alternatively propose an end-to-end transformer-based model which uses class tokens to explicitly capture implicit class knowledge to perform RGB-D co-salient object detection, denoted as CTNet. Specifically, we first design adaptive class tokens for individual images to explore intra-saliency cues and then develop common class tokens for the whole group to explore inter-saliency cues. Besides, we also leverage the complementary cues between RGB images and depth maps to promote the learning of the above two types of class tokens. In addition, to promote model evaluation, we construct a challenging and large-scale benchmark dataset, named RGBD CoSal1k, which collects 106 groups containing 1000 pairs of RGB-D images with complex scenarios and diverse appearances. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method.

The existing saliency detection models based on RGB colors only leverage appearance cues to detect salient objects. Depth information also plays a very important role in visual saliency detection and can supply complementary cues for saliency detection. Although many RGB-D saliency models have been proposed, they require to acquire depth data, which is expensive and not easy to get. In this paper, we propose to estimate depth information from monocular RGB images and leverage the intermediate depth features to enhance the saliency detection performance in a deep neural network framework. Specifically, we first use an encoder network to extract common features from each RGB image and then build two decoder networks for depth estimation and saliency detection, respectively. The depth decoder features can be fused with the RGB saliency features to enhance their capability. Furthermore, we also propose a novel dense multiscale fusion model to densely fuse multiscale depth and RGB features based on the dense ASPP model. A new global context branch is also added to boost the multiscale features. Experimental results demonstrate that the added depth cues and the proposed fusion model can both improve the saliency detection performance. Finally, our model not only outperforms state-of-the-art RGB saliency models, but also achieves comparable results compared with state-of-the-art RGB-D saliency models.

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain. To relieve the burden of data annotation, we present the first weakly super-vised video salient object detection model based on relabeled “fixation guided scribble annotations”. Specifically, an "Appearance-motion fusion module" and bidirectional ConvLSTM based framework are proposed to achieve effective multi-modal learning and long-term temporal context modeling based on our new weak annotations. Further, we design a novel foreground-background similarity loss to further explore the labeling similarity across frames. A weak annotation boosting strategy is also introduced to boost our model performance with a new pseudo-label generation technique. Extensive experimental results on six benchmark video saliency detection datasets illustrate the effectiveness of our solution1.

Existing state-of-the-art saliency detection methods heavily rely on CNN-based architectures. Alternatively, we rethink this task from a convolution-free sequence-to-sequence perspective and predict saliency by modeling long-range dependencies, which can not be achieved by convolution. Specifically, we develop a novel unified model based on a pure transformer, namely, Visual Saliency Transformer (VST), for both RGB and RGB-D salient object detection (SOD). It takes image patches as inputs and leverages the transformer to propagate global contexts among image patches. Unlike conventional architectures used in Vision Transformer (ViT), we leverage multi-level token fusion and propose a new token upsampling method under the transformer framework to get high-resolution detection results. We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism. Experimental results show that our model outperforms existing methods on both RGB and RGB-D SOD benchmark datasets. Most importantly, our whole framework not only provides a new perspective for the SOD field but also shows a new paradigm for transformer-based dense prediction models. Code is available at https://github.com/nnizhang/VST.

The application of light field data in salient object detection is becoming increasingly popular recently. The difficulty lies in how to effectively fuse the features within the focal stack and how to cooperate them with the feature of the all-focus image. Previous methods usually fuse focal stack features via convolution or ConvLSTM, which are both less effective and ill-posed. In this paper, we model the information fusion within focal stack via graph networks. They introduce powerful context propagation from neighbouring nodes and also avoid ill-posed implementations. On the one hand, we construct local graph connections thus avoiding prohibitive computational costs of traditional graph networks. On the other hand, instead of processing the two kinds of data separately, we build a novel dual graph model to guide the focal stack fusion process using all-focus patterns. To handle the second difficulty, previous methods usually implement one-shot fusion for focal stack and all-focus features, hence lacking a thorough exploration of their supplements. We introduce a reciprocative guidance scheme and enable mutual guidance between these two kinds of information at multiple steps. As such, both kinds of features can be enhanced iteratively, finally benefiting the saliency prediction. Extensive experimental results show that the proposed models are all beneficial and we achieve significantly better results than state-of-the-art methods.

Humans perform co-saliency detection by first summarizing the consensus knowledge in the whole group and then searching corresponding objects in each image. Previous methods usually lack robustness, scalability, or stability for the first process and simply fuse consensus features with image features for the second process. In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process. To summarize consensus image features, we first summarize robust features for every single image using an effective pooling method and then aggregate cross-image consensus cues via the self-attention mechanism. By doing this, our model meets the scalability and stability requirements. Next, we generate dynamic kernels from consensus features to encode the summarized consensus knowledge. Two kinds of kernels are generated in a supplementary way to summarize fine-grained image-specific consensus object cues and the coarse group-wise common knowledge, respectively. Then, we can effectively perform object searching by employing dynamic convolution at multiple scales. Besides, a novel and effective data synthesis method is also proposed to train our network. Experimental results on four benchmark datasets verify the effectiveness of our proposed method. Our code and saliency maps are available at https://github.com/nnizhang/CADC.

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.

Different from conventional instance segmentation, salient instance segmentation (SIS) faces two difficulties. The first is that it involves segmenting salient instances only while ignoring background, and the second is that it targets generic object instances without pre-defined object categories. In this paper, based on the state-of-the-art Mask R-CNN model, we propose to leverage complementary saliency and contour information to handle these two challenges. We first improve Mask R-CNN by introducing an interleaved execution strategy and proposing a novel mask head network to incorporate global context within each RoI. Then we add two branches to Mask R-CNN for saliency and contour detection, respectively. We fuse the Mask R-CNN features with the saliency and contour features, where the former supply pixel-wise saliency information to help with identifying salient regions and the latter provide a generic object contour prior to help detect and segment generic objects. We also propose a novel multiscale global attention model to generate attentive global features from multiscale representative features for feature fusion. Experimental results demonstrate that all our proposed model components can improve SIS performance. Finally, our overall model outperforms state-of-the-art SIS methods and Mask R-CNN by more than 6% and 3%, respectively. By using additional multitask training data, we can further improve the model performance on the ILSO dataset.

Group re-identification aims to match groups of people across disjoint cameras. In this task, the contextual information from neighbor individuals can be exploited for re-identifying each individual within the group as well as the entire group. However, compared with single person re-identification, it brings new challenges including group layout and group membership changes. Motivated by the observation that individuals who are close together are more likely to keep in the same group under different cameras than those who are far apart, we propose to model each group as a spatial K-nearest neighbor graph (SKNNG) and design a group context graph neural network (GCGNN) for graph representation learning. Specifically, for each node in the graph, the proposed GCGNN learns an embedding which aggregates the contextual information from neighbor nodes. We design multiple weighting kernels for neighborhood aggregation based on the graph properties including node in-degrees and spatial relationship attributes. We compute the similarity scores between node embeddings of two graphs for group member association and obtain the matching score between the two graphs by summing up the similarity scores of all linked node pairs. Experimental results on three public datasets show that our approach performs favorably against state-of-the-art methods and achieves high efficiency.

Saliency detection on RGB-D images is receiving more and more research interests recently. Previous models adopt the early fusion or the result fusion scheme to fuse the input RGB and depth data or their saliency maps, which incur the problem of distribution gap or information loss. Some other models use the feature fusion scheme but are limited by the linear feature fusion methods. In this paper, we propose to fuse attention learned in both modalities. Inspired by the Non-local model, we integrate the self-attention and each other's attention to propagate long-range contextual dependencies, thus incorporating multi-modal information to learn attention and propagate contexts more accurately. Considering the reliability of the other modality's attention, we further propose a selection attention to weight the newly added attention term. We embed the proposed attention module in a two-stream CNN for RGB-D saliency detection. Furthermore, we also propose a residual fusion module to fuse the depth decoder features into the RGB stream. Experimental results on seven benchmark datasets demonstrate the effectiveness of the proposed model components and our final saliency model. Our code and saliency maps are available at https://github.com/nnizhang/S2MA.

Existing saliency models typically incorporate contexts holistically. However, for each pixel, usually only part of its context region contributes to saliency prediction, while other parts are likely either noise or distractions. In this paper, we propose a novel pixel-wise contextual attention network (PiCANet) to selectively attend to informative context locations at each pixel. The proposed PiCANet generates an attention map over the contextual region of each pixel and construct attentive contextual features via selectively incorporating the features of useful context locations. We present three formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts. All the three models are fully differentiable and can be integrated with convolutional neural networks with joint training. In this work, we introduce the proposed PiCANets into a U-Net model for salient object detection. The generated global and local attention maps can learn to incorporate global contrast and regional smoothness, which help localize and highlight salient objects more accurately and uniformly. Experimental results show that the proposed PiCANets perform effectively for saliency detection against the state-of-the-art methods. Furthermore, we demonstrate the effectiveness and generalization ability of the PiCANets on semantic segmentation and object detection with improved performance.

Contexts play an important role in the saliency detection task. However, given a context region, not all contextual information is helpful for the final task. In this paper, we propose a novel pixel-wise contextual attention network, i.e., the PiCANet, to learn to selectively attend to informative context locations for each pixel. Specifically, for each pixel, it can generate an attention map in which each attention weight corresponds to the contextual relevance at each context location. An attended contextual feature can then be constructed by selectively aggregating the contextual information. We formulate the proposed PiCANet in both global and local forms to attend to global and local contexts, respectively. Both models are fully differentiable and can be embedded into CNNs for joint training. We also incorporate the proposed models with the U-Net architecture to detect salient objects. Extensive experiments show that the proposed PiCANets can consistently improve saliency detection performance. The global and local PiCANets facilitate learning global contrast and homogeneousness, respectively. As a result, our saliency model can detect salient objects more accurately and uniformly, thus performing favorably against the state-of-the-art methods.

Salient object detection from RGB-D images aims to utilize both the depth view and RGB view to automatically localize objects of human interest in the scene. Although a few earlier efforts have been devoted to the study of this paper in recent years, two major challenges still remain: 1) how to leverage the depth view effectively to model the depth-induced saliency and 2) how to implement an optimal combination of the RGB view and depth view, which can make full use of complementary information among them. To address these two challenges, this paper proposes a novel framework based on convolutional neural networks (CNNs), which transfers the structure of the RGB-based deep neural network to be applicable for depth view and fuses the deep representations of both views automatically to obtain the final saliency map. In the proposed framework, the first challenge is modeled as a cross-view transfer problem and addressed by using the task-relevant initialization and adding deep supervision in hidden layer. The second challenge is addressed by a multiview CNN fusion model through a combination layer connecting the representation layers of RGB view and depth view. Comprehensive experiments on four benchmark datasets demonstrate the significant and consistent improvements of the proposed approach over other state-of-the-art methods.

Traditional saliency models usually adopt hand-crafted image features and human-designed mechanisms to calculate local or global contrast. In this paper, we propose a novel computational saliency model, i.e., deep spatial contextual long-term recurrent convolutional network (DSCLRCN), to predict where people look in natural scenes. DSCLRCN first automatically learns saliency related local features on each image location in parallel. Then, in contrast with most other deep network based saliency models which infer saliency in local contexts, DSCLRCN can mimic the cortical lateral inhibition mechanisms in human visual system to incorporate global contexts to assess the saliency of each image location by leveraging the deep spatial long short-term memory (DSLSTM) model. Moreover, we also integrate scene context modulation in DSLSTM for saliency inference, leading to a novel deep spatial contextual LSTM (DSCLSTM) model. The whole network can be trained end-to-end and works efficiently when testing. Experimental results on two benchmark datasets show that DSCLRCN can achieve state-of-the-art performance on saliency detection. Furthermore, the proposed DSCLSTM model can significantly boost the saliency detection performance by incorporating both global spatial interconnections and scene context modulation, which may uncover novel inspirations for studies on them in computational saliency models.

Weakly supervised video object segmentation (WSVOS) focuses on generating pixel-level object masks for videos only tagged with class labels, which is an essential yet challenging task. For WSVOS, the algorithm is just aware of rough category information rather than the concrete object size and location cues, besides it lacks reliable annotated exemplars to learn temporal evolution in the investigated videos. Basically, there are three challenging factors which may influence the performance of WSVOS: foreground object discovery in each frame, coarse object semantic consistency within each video, and fine-grained segmentation smoothness within neighbor frames. In this paper, we establish a semantic ranking and optical warping network (SROWN) to simultaneously solve these three challenges in a unified framework. For the first challenge, we apply the still image saliency detection method and discover the foreground object for each frame via a segmentation network. Due to the huge discrepancies between the image saliency and the video object segmentation, we step further and propose two subnetworks to solve the other two challenges. For the second one, we propose an attentive semantic ranking subnetwork to mine video-level tags, which can learn discriminative features for semantic ranking and lead to semantic consistent segmentation masks. For the third one, we propose an optical flow warping subnetwork to constrain fine-grained segmentation smoothness within neighbor frames, which can suppress the large deformation and thus obtain smooth object boundaries for adjacent frames. Experiments on two benchmark datasets, i.e., DAVIS dataset and YouTube-Objects dataset, demonstrate the effectiveness of the proposed approach for segmenting out video objects under weak supervision.

We propose a novel attention framework called attentive linear transformation (ALT). Instead of learning the spatial or channel-wise attention in existing models, ALT learns to attend to the high-dimensional transformation matrix from the image feature space to the context vector space. Thus ALT can learn various relevant feature abstractions, including spatial attention, channel-wise attention and visual dependence. Besides, we propose a soft threshold regression to predict the attention probabilities for local regions. Soft threshold regression preserves more useful visual information than popular softmax regression. Extensive experiments on the MS COCO and the Flickr30k datasets demonstrate the superiority of our model compared with other state-of-the-art methods.

Eye movements in the case of freely viewing natural scenes are believed to be guided by local contrast, global contrast, and top-down visual factors. Although a lot of previous works have explored these three saliency cues for several years, there still exists much room for improvement on how to model them and integrate them effectively. This paper proposes a novel computation model to predict eye fixations, which adopts a multiresolution convolutional neural network (Mr-CNN) to infer these three types of saliency cues from raw image data simultaneously. The proposed Mr-CNN is trained directly from fixation and nonfixation pixels with multiresolution input image regions with different contexts. It utilizes image pixels as inputs and eye fixation points as labels. Then, both the local and global contrasts are learned by fusing information in multiple contexts. Meanwhile, various top-down factors are learned in higher layers. Finally, optimal combination of top-down factors and bottom-up contrasts can be learned to predict eye fixations. The proposed approach significantly outperforms the state-of-the-art methods on several publically available benchmark databases, demonstrating the superiority of Mr-CNN. We also apply our method to the RGB-D image saliency detection problem. Through learning saliency cues induced by depth and RGB information on pixel level jointly and their interactions, our model achieves better performance on predicting eye fixations in RGB-D images.

Traditional salient object detection models often use hand-crafted features to formulate contrast and various prior knowledge, and then combine them artificially. In this work, we propose a novel end-to-end deep hierarchical saliency network (DHSNet) based on convolutional neural networks for detecting salient objects. DHSNet first makes a coarse global prediction by automatically learning various global structured saliency cues, including global contrast, objectness, compactness, and their optimal combination. Then a novel hierarchical recurrent convolutional neural network (HRCNN) is adopted to further hierarchically and progressively refine the details of saliency maps step by step via integrating local context information. The whole architecture works in a global to local and coarse to fine manner. DHSNet is directly trained using whole images and corresponding ground truth saliency masks. When testing, saliency maps can be generated by directly and efficiently feed forwarding testing images through the network, without relying on any other techniques. Evaluations on four benchmark datasets and comparisons with other 11 state-of-the-art algorithms demonstrate that DHSNet not only shows its significant superiority in terms of performance, but also achieves a real-time speed of 23 FPS on modern GPUs.

It is believed that eye movements in free-viewing of natural scenes are directed by both bottom-up visual saliency and top-down visual factors. In this paper, we propose a novel computational framework to simultaneously learn these two types of visual features from raw image data using a multiresolution convolutional neural network (Mr-CNN) for predicting eye fixations. The Mr-CNN is directly trained from image regions centered on fixation and non-fixation locations over multiple resolutions, using raw image pixels as inputs and eye fixation attributes as labels. Diverse top-down visual features can be learned in higher layers. Meanwhile bottom-up visual saliency can also be inferred via combining information over multiple resolutions. Finally, optimal integration of bottom-up and top-down cues can be learned in the last logistic regression layer to predict eye fixations. The proposed approach achieves state-of-the-art results over four publically available benchmark datasets, demonstrating the superiority of our work.