# Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection

arXiv: https://arxiv.org/abs/2010.05537 · HTML: https://mlsanity.com/paper/2010.05537/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 30 of 38)

- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications](https://mlsanity.com/paper/2304.05750/) (2023)
- [SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection](https://mlsanity.com/paper/2204.05585/) (2022)
- [C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection](https://mlsanity.com/paper/2306.16175/) (2023)
- [VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning](https://mlsanity.com/paper/2311.15011/) (2023)
- [Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection](https://mlsanity.com/paper/2107.01779/) (2021)
- [VST++: Efficient and Stronger Visual Saliency Transformer](https://mlsanity.com/paper/2310.11725/) (2023)
- [Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM](https://mlsanity.com/paper/2404.04996/) (2024)
- [Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark](https://mlsanity.com/paper/2406.00917/) (2024)
- [Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection](https://mlsanity.com/paper/2406.01127/) (2024)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [Osmosis: RGBD Diffusion Prior for Underwater Image Restoration](https://mlsanity.com/paper/2403.14837/) (2024)
- [DC-Net: Divide-and-Conquer for Salient Object Detection](https://mlsanity.com/paper/2305.14955/) (2023)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance Segmentation](https://mlsanity.com/paper/2307.08098/) (2023)
- [Salient Object Detection in RGB-D Videos](https://mlsanity.com/paper/2310.15482/) (2023)
- [Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection](https://mlsanity.com/paper/2405.05614/) (2024)
- [ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection](https://mlsanity.com/paper/2406.12536/) (2024)
- [MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2410.15015/) (2024)
- [DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation](https://mlsanity.com/paper/2406.03702/) (2024)
- [ASOD60K: An Audio-Induced Salient Object Detection Dataset for Panoramic Videos](https://mlsanity.com/paper/2107.11629/) (2021)
- [Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2206.03105/) (2022)
- [CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection](https://mlsanity.com/paper/2407.06780/) (2024)
- [Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations](https://mlsanity.com/paper/2410.16953/) (2024)
- [Depth-guided Texture Diffusion for Image Semantic Segmentation](https://mlsanity.com/paper/2408.09097/) (2024)
- [Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection](https://mlsanity.com/paper/2411.18409/) (2024)
- [SiaTrans: Siamese Transformer Network for RGB-D Salient Object Detection with Depth Image Classification](https://mlsanity.com/paper/2207.04224/) (2022)
- [A Volumetric Saliency Guided Image Summarization for RGB-D Indoor Scene Classification](https://mlsanity.com/paper/2401.16227/) (2024)
- [Large coordinate kernel attention network for lightweight image super-resolution](https://mlsanity.com/paper/2405.09353/) (2024)

## Abstract (arXiv)

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