mlsanityData to 14 Oct 2026

HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection

arXiv 2307.00954 ↗First posted 3 Jul 2023cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

RGB-D salient object detection (SOD) aims to detect the prominent regions by jointly modeling RGB and depth information. Most RGB-D SOD methods apply the same type of backbones and fusion modules to identically learn the multimodality and multistage features. However, these features contribute differently to the final saliency results, which raises two issues: 1) how to model discrepant characteristics of RGB images and depth maps; 2) how to fuse these cross-modality features in different stages. In this paper, we propose a high-order discrepant interaction network (HODINet) for RGB-D SOD. Concretely, we first employ transformer-based and CNN-based architectures as backbones to encode RGB and depth features, respectively. Then, the high-order representations are delicately extracted and embedded into spatial and channel attentions for cross-modality feature fusion in different stages. Specifically, we design a high-order spatial fusion (HOSF) module and a high-order channel fusion (HOCF) module to fuse features of the first two and the last two stages, respectively. Besides, a cascaded pyramid reconstruction network is adopted to progressively decode the fused features in a top-down pathway. Extensive experiments are conducted on seven widely used datasets to demonstrate the effectiveness of the proposed approach. We achieve competitive performance against 24 state-of-the-art methods under four evaluation metrics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 76 references that are in the map. First posted on arXiv 3 Jul 2023.

Builds on

39 of 76 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  8. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  9. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  10. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  11. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  12. 2014Deeply-Supervised Netscited by 367
27 more
  1. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  2. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  3. 2021Visual Saliency Transformercited by 175
  4. 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 164
  5. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  6. 2015Salient Object Detection: A Benchmarkcited by 131
  7. 2020Strip Pooling: Rethinking Spatial Pooling for Scene Parsingcited by 114
  8. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  9. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  10. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  11. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
  12. 2020A Single Stream Network for Robust and Real-time RGB-D Salient Object Detectioncited by 67
  13. 2019Mixed High-Order Attention Network for Person Re-Identificationcited by 65
  14. 2018Review of Visual Saliency Detection with Comprehensive Informationcited by 60
  15. 2022SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detectioncited by 59
  16. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  17. 2020Accurate RGB-D Salient Object Detection via Collaborative Learningcited by 52
  18. 2020Cross-Modal Weighting Network for RGB-D Salient Object Detectioncited by 47
  19. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  20. 2016Low-rank Bilinear Pooling for Fine-Grained Classificationcited by 42
  21. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  22. 2021RGB-D Salient Object Detection via 3D Convolutional Neural Networkscited by 36
  23. 2021Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detectioncited by 34
  24. 2020MobileSal: Extremely Efficient RGB-D Salient Object Detectioncited by 25
  25. 2019cmSalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networkscited by 21
  26. 2020Depth Quality Aware Salient Object Detectioncited by 17
  27. 2020Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detectioncited by 13

Built on by

Not cited yet.