# Robust RGB-D Fusion for Saliency Detection

arXiv: https://arxiv.org/abs/2208.01762 · HTML: https://mlsanity.com/paper/2208.01762/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 2 Aug 2022.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [A Simple Pooling-Based Design for Real-Time Salient Object Detection](https://mlsanity.com/paper/1904.09569/) (2019)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [Salient Object Detection: A Survey](https://mlsanity.com/paper/1411.5878/) (2014)
- [JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection](https://mlsanity.com/paper/2004.08515/) (2020)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [RGB-D Salient Object Detection: A Survey](https://mlsanity.com/paper/2008.00230/) (2020)
- [Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2007.06227/) (2020)
- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection](https://mlsanity.com/paper/2007.06811/) (2020)
- [Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion](https://mlsanity.com/paper/2103.11832/) (2021)
- [Accurate RGB-D Salient Object Detection via Collaborative Learning](https://mlsanity.com/paper/2007.11782/) (2020)

## Built on by (most cited first, 12 of 12)

- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [RGB-Event Fusion for Moving Object Detection in Autonomous Driving](https://mlsanity.com/paper/2209.08323/) (2022)
- [HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness](https://mlsanity.com/paper/2301.07405/) (2023)
- [PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration](https://mlsanity.com/paper/2308.04782/) (2023)
- [Object Segmentation by Mining Cross-Modal Semantics](https://mlsanity.com/paper/2305.10469/) (2023)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection](https://mlsanity.com/paper/2405.05614/) (2024)
- [Pyramid Deep Fusion Network for Two-Hand Reconstruction from RGB-D Images](https://mlsanity.com/paper/2307.06038/) (2023)
- [Depth-guided Texture Diffusion for Image Semantic Segmentation](https://mlsanity.com/paper/2408.09097/) (2024)
- [RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation](https://mlsanity.com/paper/2609.12622/) (2026)
- [CSDNet: Detect Salient Object in Depth-Thermal via A Lightweight Cross Shallow and Deep Perception Network](https://mlsanity.com/paper/2403.10104/) (2024)
- [Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing](https://mlsanity.com/paper/2502.06219/) (2025)

## Abstract (arXiv)

Efficiently exploiting multi-modal inputs for accurate RGB-D saliency detection is a topic of high interest. Most existing works leverage cross-modal interactions to fuse the two streams of RGB-D for intermediate features' enhancement. In this process, a practical aspect of the low quality of the available depths has not been fully considered yet. In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB. To this end, we propose a robust RGB-D fusion method that benefits from (1) layer-wise, and (2) trident spatial, attention mechanisms. On the one hand, layer-wise attention (LWA) learns the trade-off between early and late fusion of RGB and depth features, depending upon the depth accuracy. On the other hand, trident spatial attention (TSA) aggregates the features from a wider spatial context to address the depth misalignment problem. The proposed LWA and TSA mechanisms allow us to efficiently exploit the multi-modal inputs for saliency detection while being robust against low-quality depths. Our experiments on five benchmark datasets demonstrate that the proposed fusion method performs consistently better than the state-of-the-art fusion alternatives.