Underwater salient object detection (USOD) poses a significantly greater challenge than traditional terrestrial scenes, due to both the complex image degradation and the absence of multimodal information in underwater environments. Existing image enhancement methods are not specifically optimized for USOD, while current USOD approaches rarely consider effective extraction and utilization of multimodal information, leading to limited performance. This paper proposes HydroDepthAwareNet (HDANet), which addresses these challenges through developing targeted designs to enhance USOD performance. It first integrates a task-driven underwater image enhancement module, named HydroDepthEnhanceModule (HDEM), which is based on physical models to provide enhanced images and multimodal information optimized for USOD tasks. Furthermore, we develop a physics-inspired three-way unsupervised learning strategy, leveraging the complementary effects of re-enhancement and re-degradation to improve HDEM’s generalization across diverse underwater image degradation scenarios. Additionally, we design a robust cross-attention (RCA) module to effectively fuse multimodal features while mitigating noise and blurring by exploiting channel and spatial cross-attention mechanisms. Extensive experiments on various USOD datasets demonstrate that the proposed HDANet significantly outperforms existing state-of-the-art methods. The source code will be made available at https://github.com/mikurules/USOD-HDANet.

Salient object detection in optical remote sensing images (ORSI-SOD) aims to segment salient regions from high-resolution remote sensing images. However, most existing ORSI-SOD methods primarily rely on feature learning of regions to address the issue of blurred edges, while neglecting the potential advantages of similarity calculation in inferring edge clues. To overcome this issue, we propose a novel network with similarity perception termed edge-guided refinement network (ERNet), which distinguishes the edge region of salient objects from coarse to fine through two-stage similarity calculation. Firstly, we introduce the adaptive uncertainty calibration module (AUCM), which utilizes the proposed similarity-based edge perception mechanism (SEPM) to adaptively calibrate edge uncertain information. Secondly, to effectively capture global semantic information, we propose the hierarchical semantic reconstruction module (HSRM), which comprehensively correlates different levels of semantic clues from both internal and external perspectives. Finally, to supplement the local detail of salient objects, we design the dynamic detail interaction module (DDIM), which dynamically extracts detail information of objects at different scales. Extensive experiments on three challenging benchmark datasets have demonstrated the remarkable superiority of our ERNet compared to 30 state-of-the-art models. The source codes will be publicly available at https://github.com/xinwang11/ERNet.

The stable diffusion model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these approaches typically maintain the original network architecture. The extensive parameter scale and substantial computational demands have limited research into adjusting the model architecture. This study focuses on reducing redundant computation in SDM and optimizes the model through both tuning and tuning-free methods: 1) for the tuning method, we design a model assembly strategy to reconstruct a lightweight model while preserving performance and ensuring semantic stability through distillation and 2) for the tuning-free method, we propose a feature inheritance strategy to accelerate inference by skipping local computations at the block, layer, or unit level within the network structure. We also examine multiple sampling modes for feature inheritance at the time-step level. Experiments demonstrate that both the proposed tuning and the tuning-free methods can improve the speed and performance of the SDM. The lightweight model reconstructed by the model assembly strategy increases generation speed by 22.4%, while the feature inheritance strategy enhances the SDM generation speed by 40.0%.

Recent progress in salient object detection (SOD) mainly depends on the Atrous Spatial Pyramid Pooling (ASPP) module for multi-scale learning. Intuitively, different input images, different pixels, and different network layers may have different preferences for various feature scales. However, ASPP treats all feature scales as equally important by a simple sum operation. To this end, we propose Attentive Atrous Spatial Pyramid Pooling (A2SPP) by adding a new Cubic Information-Embedding Attention (CIEA) module at each branch of ASPP. In this way, each position in the 3D feature map can automatically learn the feature scales it prefers. Specifically, CIEA consists of Spatial-Embedding Channel Attention (SECA) and Channel-Embedding Spatial Attention (CESA). Instead of the previous direct squeeze and ignoring of one dimension when computing the attention for the other dimension, SECA/CESA attempts to embed spatial/channel information into channel/spatial attention, respectively. In addition, CIEA learns SECA and CESA for each 3D position simultaneously rather than previous separate computation of channel and spatial attention for each 2D position. Incorporating A2SPP and CIEA, the proposed A2SPPNet performs favorably against previous state-of-the-art SOD methods.

Effective fusion of different types of features is the key to salient object detection (SOD). The majority of the existing network structure designs are based on the subjective experience of scholars, and the process of feature fusion does not consider the relationship between the fused features and the highest-level features. In this paper, we focus on the feature relationship and propose a novel global attention unit, which we term the “perception-and-regulation” (PR) block, that adaptively regulates the feature fusion process by explicitly modelling the interdependencies between features. The perception part uses the structure of the fully connected layers in the classification networks to learn the size and shape of the objects. The regulation part selectively strengthens and weakens the features to be fused. An imitating eye observation module (IEO) is further employed to improve the global perception capabilities of the network. The imitation of foveal vision and peripheral vision enables the IEO to scrutinize highly detailed objects and to organize a broad spatial scene to better segment objects. Sufficient experiments conducted on the SOD datasets demonstrate that the proposed method performs favourably against the 29 state-of-the-art methods.

Salient object detection (SOD) aims to detect the most prominent objects and regions in the human vision. Since the RGB and depth modalities contain discrepant characteristics and convey the clues of different domains, how to explore the fusion of multi-modal information and the interaction of cross-stage features remain the key problems in RGB-D SOD. In this letter, we propose a cross-stage multi-scale interaction network (CMINet), consisting of a multi-scale spatial pooling (MSP) module and a cross-stage pyramid interaction (CPI) module to interweave the feature maps of different stages in a bottom-up and top-down way. In addition, we also design an adaptive weight fusion (AWF) module to weigh the importance of multimodality features and fuse them. Extensive experiments are conducted on 4 widely used datasets to validate the effectiveness of the proposed CMINet. The results demonstrate that our approach achieves state-of-the-art performance against other 11 methods under 4 evaluation metrics.

The multi-modal salient object detection model based on RGB-D information has better robustness in the real world. However, it remains nontrivial to better adaptively balance multi-modal information in the feature fusion phase. In this letter, we propose a novel gated recoding network (GRNet) to evaluate the information validity of the two modes and balance their influence. Our framework is divided into three phases: perception phase, recoding mixing phase, and integration phase. Specifically, a perception encoder is adopted to extract multi-level single-modal features, which lays the foundation for multi-modal semantic comparative analysis. Then, a modal-adaptive gate unit (MGU) is proposed to suppress the invalid information and transfer the effective modal features to the recoding mixer and the hybrid branch decoder. The recoding mixer is responsible for recoding and mixing the balanced multi-modal information. Finally, the hybrid branch decoder completes the multi-level feature integration under the guidance of an optional edge guidance stream (OEGS). Experiments on 8 popular benchmarks verify that our framework has better overall performance than the other 28 state-of-the-art algorithms.

Camouflaged objects, similar to the background, show indefinable boundaries and deceptive textures, which increases the difficulty of detection task and makes the model rely on features with more information. Herein, we design a texture label to facilitate our network for accurate camouflaged object segmentation. Motivated by the complementary relationship between texture labels and camouflaged object labels, we propose an interactive guidance framework named TINet, which focuses on finding the indefinable boundary and the texture difference by progressive interactive guidance. It maximizes the guidance effect of refined multi-level texture cues on segmentation. Specifically, texture perception decoder (TPD) makes a comprehensive analysis of texture information in multiple scales. Feature interaction guidance decoder (FGD) interactively refines multi-level features of camouflaged object detection and texture detection level by level. Holistic perception decoder (HPD) enhances FGD results by multi-level holistic perception. In addition, we propose a boundary weight map to help the loss function pay more attention to the object boundary. Sufficient experiments conducted on COD and SOD datasets demonstrate that the proposed method performs favorably against 23 state-of-the-art methods.