mlsanityData to 7 Oct 2026

Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion

arXiv 2103.11832 ↗First posted 22 Mar 2021cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

RGB-D salient object detection (SOD) is usually formulated as a problem of classification or regression over two modalities, i.e., RGB and depth. Hence, effective RGBD feature modeling and multi-modal feature fusion both play a vital role in RGB-D SOD. In this paper, we propose a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects. In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry prior. Moreover, to perform effective multi-modal feature fusion, we further present an automatic architecture search approach for RGB-D SOD, which does well in finding out a feasible architecture from our specially designed multi-modal multi-scale search space. Extensive experiments on seven standard benchmarks demonstrate the effectiveness of the proposed approach against the state-of-the-art.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 30 of its 66 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

30 of 66 references.

References · 30

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  5. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  8. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  9. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  10. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  11. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  12. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
18 more
  1. 2015Salient Object Detection: A Benchmarkcited by 130
  2. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  3. 2019MFAS: Multimodal Fusion Architecture Searchcited by 84
  4. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  5. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
  6. 2020A Single Stream Network for Robust and Real-time RGB-D Salient Object Detectioncited by 67
  7. 2020Accurate RGB-D Salient Object Detection via Collaborative Learningcited by 52
  8. 2020RGB-D Salient Object Detection with Cross-Modality Modulation and Selectioncited by 50
  9. 2020Cross-Modal Weighting Network for RGB-D Salient Object Detectioncited by 47
  10. 2016RGBD Salient Object Detection via Deep Fusioncited by 46
  11. 2020Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detectioncited by 40
  12. 2020Cascade Graph Neural Networks for RGB-D Salient Object Detectioncited by 36
  13. 2020Deep Multimodal Neural Architecture Searchcited by 34
  14. 2015Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Networkcited by 31
  15. 2019Graph-guided Architecture Search for Real-time Semantic Segmentationcited by 28
  16. 2018PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detectioncited by 21
  17. 2017Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down featurescited by 7
  18. 2018RealPoint3D: Point Cloud Generation from a Single Image with Complex Backgroundcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 17; 2023: 15; 2024: 10; 2025: 6; 2026: 3.

56 papers.

Sort:

By area:

  1. 2022SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detectioncited by 59
  2. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 58
  3. 2021Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Predictioncited by 57
  4. 2022Dynamic Multimodal Fusioncited by 54
  5. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  6. 2023MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learningcited by 40
  7. 2023HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awarenesscited by 31
  8. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  9. 2024Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detectioncited by 27
  10. 2022Glass Segmentation with RGB-Thermal Image Pairscited by 26
  11. 2022SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detectioncited by 26
  12. 2021Event-guided Deblurring of Unknown Exposure Time Videoscited by 25
38 more
  1. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  2. 2022Texture-guided Saliency Distilling for Unsupervised Salient Object Detectioncited by 24
  3. 2024Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmarkcited by 19
  4. 2024Learning Adaptive Fusion Bank for Multi-modal Salient Object Detectioncited by 19
  5. 2023Towards Diverse Binary Segmentation via A Simple yet General Gated Networkcited by 17
  6. 2024Robust Multimodal Learning via Representation Decouplingcited by 17
  7. 2025Improving Multimodal Learning via Imbalanced Learningcited by 16
  8. 2025Boosting Multimodal Learning via Disentangled Gradient Learningcited by 15
  9. 2022Joint Learning of Salient Object Detection, Depth Estimation and Contour Extractioncited by 12
  10. 2022Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detectioncited by 12
  11. 2022Robust RGB-D Fusion for Saliency Detectioncited by 12
  12. 2023Object Segmentation by Mining Cross-Modal Semanticscited by 12
  13. 2024MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modalitycited by 10
  14. 2023Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detectioncited by 9
  15. 2023Unified-modal Salient Object Detection via Adaptive Prompt Learningcited by 9
  16. 2021Modality-Guided Subnetwork for Salient Object Detectioncited by 8
  17. 2023Adaptive Multi-source Predictor for Zero-shot Video Object Segmentationcited by 7
  18. 2026Unbiased Dynamic Multimodal Fusioncited by 7
  19. 2024Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidancecited by 6
  20. 2025Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspectivecited by 6
  21. 2022Trichomonas Vaginalis Segmentation in Microscope Imagescited by 5
  22. 2024TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Taskscited by 5
  23. 2022Pyramidal Attention for Saliency Detectioncited by 4
  24. 2024GazeFusion: Saliency-Guided Image Generationcited by 4
  25. 2022An Energy-Based Prior for Generative Saliencycited by 3
  26. 2023ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformercited by 3
  27. 2024CLASH: Complementary Learning with Neural Architecture Search for Gait Recognitioncited by 3
  28. 2022Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Imagescited by 2
  29. 2022Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detectioncited by 2
  30. 2023NUAA-QMUL-AIIT at Memotion 3: Multi-modal Fusion with Squeeze-and-Excitation for Internet Meme Emotion Analysiscited by 2
  31. 2023Multimodal Transformer Using Cross-Channel attention for Object Detection in Remote Sensing Imagescited by 2
  32. 2024AdaFlow: Opportunistic Inference on Asynchronous Mobile Data with Generalized Affinity Controlcited by 2
  33. 2026STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detectioncited by 2
  34. 2026PDMP: Rethinking Balanced Multimodal Learning via Performance-Dominant Modality Prioritizationcited by 1
  35. 2021A General Divergence Modeling Strategy for Salient Object Detectioncited by 0
  36. 2022Multi-Scale Iterative Refinement Network for RGB-D Salient Object Detectioncited by 0
  37. 2022Dynamic Message Propagation Network for RGB-D Salient Object Detectioncited by 0
  38. 2022TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detectioncited by 0

50 most cited of 56 All 56 (JSON)