This paper delves into the task of arbitrary modality salient object detection (AM SOD), aiming to detect salient objects from the images with arbitrary modality types or arbitrary modality numbers by using a single model trained once. Specifically, we develop a novel model, termed modality adaptive network (MAN), for AM SOD, which addresses two fundamental challenges in AM SOD: the diverse modality discrepancies arising from varying modality types and the dynamic fusion dilemma resulting from an unfixed number of modalities in the input data. Technically, MAN first introduces a novel Modality-Adaptive Feature Extractor (MAFE) to adaptively extract features from different input modalities based on their characteristics by utilizing a set of learnable modality prompts. Concurrently, a new modality translation contractive (MTC) loss is devised to facilitate the training of MAFE as well as modality prompts, thereby effectively addressing the inherent modality discrepancies and extracting more discriminative features from each modality image. Subsequently, MAN presents a hybrid dynamic fusion (HDF) strategy to effectively resolve the challenge of dynamic inputs in multi-modal feature fusion as well as enhance the exploitation of complementary information across different modalities. This is specially achieved by a Channel- wise Dynamic Fusion Module (CDFM) and a Spatial- wise Dynamic Fusion Module (SDFM). Experimental results show that by virtue of MAFE, MTC loss and HDF strategy, our proposed method achieves significant increasements over existing models on benchmark datasets.

Common mechanisms for achieving object camouflage include reducing differences and increasing distractions. Such camouflage mechanisms hinder the object detectors to accurately distinguish the camouflaged objects from their surroundings. Considering that, we reexamine the camouflaged object detection (COD) task from the perspective of camouflage mechanisms and make the first attempt to discover the target objects in a de-camouflaging manner. We argue that this process can not only lead to a better understanding of camouflage, but also provide a new perspective for detecting camouflaged objects. For that, we first analyze some existing camouflage mechanisms together with their induced problems. Afterwards, considering the inner relationships between SOD and COD, we resort to the SOD task to synergistically achieve de-camouflaging for COD. Specifically, we incorporate the SOD task into the COD model and present a multi-task learning framework for COD, which models the intrinsic relationships between the two tasks from different perspectives, i.e., task-conflicting attribute and task-consistent attribute, to destroy the camouflage conditions for highlighting those inconspicuous yet valuable cues of camouflaged objects. In more detail, modeling the task-conflicting attribute is to well identify camouflaged objects by alleviating such interfering information from salient ones, and is achieved by a Gate Classification (GC) strategy and a Region Distraction Module (RDM). While, modeling the task-consistent attribute, which is achieved by an adversarial learning (AL) scheme and a Boundary Injection Module (BIM), is intended to enhance the boundary differences between the camouflaged objects and their backgrounds for fully segmenting the camouflaged objects. Extensive results demonstrate the superiorities of our proposed model over existing ones in camouflaged object detection.

Due to their imaging mechanisms and techniques, some depth images inevitably have low visual qualities or have some inconsistent foregrounds with their corresponding RGB images. Directly using such depth images will deteriorate the performance of RGB-D SOD. In view of this, a novel RGB-D salient object detection model is presented, which follows the principle of calibration-then-fusion to effectively suppress the influence of such two types of depth images on final saliency prediction. Specifically, the proposed model is composed of two stages, i.e., an image generation stage and a saliency reasoning stage. The former generates high-quality and foreground-consistent pseudo depth images via an image generation network. While the latter first calibrates the original depth information with the aid of those newly generated pseudo depth images and then performs cross-modal feature fusion for the final saliency reasoning. Especially, in the first stage, a Two-steps Sample Selection (TSS) strategy is employed to select such reliable depth images from the original RGB-D image pairs as supervision information to optimize the image generation network. Afterwards, in the second stage, a Feature Calibrating and Fusing Network (FCFNet) is proposed to achieve the calibration-then-fusion of cross-modal information for the final saliency prediction, which is achieved by a Depth Feature Calibration (DFC) module, a Shallow-level Feature Injection (SFI) module and a Multi-modal Multi-scale Fusion (MMF) module. Moreover, a loss function, i.e., Region Consistency Aware (RCA) loss, is presented as an auxiliary loss for FCFNet to facilitate the completeness of salient objects together with the reduction of background interference by considering the local regional consistency in the saliency maps. Experiments on six benchmark datasets demonstrate the superiorities of our proposed RGB-D SOD model over some state-of-the-arts.

Toward desirable saliency prediction, the types and numbers of inputs for a salient object detection (SOD) algorithm may dynamically change in many real-life applications. However, existing SOD algorithms are mainly designed or trained for one particular type of inputs, failing to be generalized to other types of inputs. Consequentially, more types of SOD algorithms need to be prepared in advance for handling different types of inputs, raising huge hardware and research costs. Differently, in this paper, we propose a new type of SOD task, termed Arbitrary Modality SOD (AM SOD). The most prominent characteristics of AM SOD are that the modality types and modality numbers will be arbitrary or dynamically changed. The former means that the inputs to the AM SOD algorithm may be arbitrary modalities such as RGB, depths, or even any combination of them. While, the latter indicates that the inputs may have arbitrary modality numbers as the input type is changed, e.g. single-modality RGB image, dual-modality RGB-Depth (RGB-D) images or triple-modality RGB-Depth-Thermal (RGB-D-T) images. Accordingly, a preliminary solution to the above challenges, i.e. a modality switch network (MSN), is proposed in this paper. In particular, a modality switch feature extractor (MSFE) is first designed to extract discriminative features from each modality effectively by introducing some modality indicators, which will generate some weights for modality switching. Subsequently, a dynamic fusion module (DFM) is proposed to adaptively fuse features from a variable number of modalities based on a novel Transformer structure. Finally, a new dataset, named AM-XD, is constructed to facilitate research on AM SOD. Extensive experiments demonstrate that our AM SOD method can effectively cope with changes in the type and number of input modalities for robust salient object detection. Our code and AM-XD dataset will be released on https://github.com/nexiakele/AMSODFirst.

Most existing RGB-D salient detection models pay more attention to the quality of the depth images, while in some special cases, the quality of RGB images may even have greater impacts on saliency detection, which has long been ignored and underestimated. To address this problem, in this paper, we present a Bi-directional Progressive Guidance Network (BPGNet) for RGB-D salient object detection, where the qualities of both RGB and depth images are involved. Since it is usually difficult to determine which modality data have low quality in advance, a bi-directional framework based on progressive guidance (PG) strategy is employed to extract and enhance the unimodal features with the aid of another modality data via the alternative interactions between the saliency prediction results and the extracted features from the multi-modality input data. Specifically, the proposed PG strategy is achieved by using the proposed Global Context Awareness (GCA), Auxiliary Feature Extraction (AFE) and Cross-modality Feature Enhancement (CFE) modules. Benefiting from the proposed PG strategy, the disturbing information within the input RGB and depth images can be well suppressed, while the discriminative information within the input images gets enhanced. On top of that, a Fusion Prediction Module (FPM) is further designed to adaptively select those features with higher discriminability as well as enhancing the common information for the final saliency prediction. Experimental results demonstrate that our proposed model is comparable to those of state-of-the-art RGB-D SOD models.

Multi-modal feature fusion and saliency reasoning are two core sub-tasks of RGB-D salient object detection. However, most existing models employ linear fusion strategies (e.g., concatenation) for multi-modal feature fusion and use a simple coarse-to-fine structure for saliency reasoning. Despite their simpleness, they can neither fully capture the cross-modal complementary information nor exploit the multi-level complementary information among the cross-modal features at different levels. To address these issues, a novel RGB-D salient object detection model is presented, where we pay special attention to the aforementioned two sub-tasks. Concretely, a multi-modal feature interaction module is first presented to explore more interactions between the unimodal RGB and depth features. It helps to capture their cross-modal complementary information by jointly using some simple linear fusion strategies and bilinear fusion ones. Then, a saliency prior information guided fusion module is presented to exploit the multi-level complementary information among the fused cross-modal features at different levels. Instead of employing a simple convolutional layer for the final saliency prediction, a saliency refinement and prediction module is designed to better exploit those extracted multi-level cross-modal information for RGB-D saliency detection. Experimental results on several benchmark datasets verify the effectiveness and superiority of the proposed framework over some state-of-the-art methods.