mlsanityData to 14 Oct 2026

Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation

arXiv 2210.15156 ↗First posted 27 Oct 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Binary segmentation is used to distinguish objects of interest from background, and is an active area of convolutional encoder-decoder network research. The current decoders are designed for specific objects based on the common backbones as the encoders, but cannot deal with complex backgrounds. Inspired by the way human eyes detect objects of interest, a new unified dual-branch decoder paradigm named the difference-aware decoder is proposed in this paper to explore the difference between the foreground and the background and separate the objects of interest in optical images. The difference-aware decoder imitates the human eye in three stages using the multi-level features output by the encoder. In Stage A, the first branch decoder of the difference-aware decoder is used to obtain a guide map. The highest-level features are enhanced with a novel field expansion module and a dual residual attention module, and are combined with the lowest-level features to obtain the guide map. In Stage B, the other branch decoder adopts a middle feature fusion module to make trade-offs between textural details and semantic information and generate background-aware features. In Stage C, the proposed difference-aware extractor, consisting of a difference guidance model and a difference enhancement module, fuses the guide map from Stage A and the background-aware features from Stage B, to enlarge the differences between the foreground and the background and output a final detection result. The results demonstrate that the difference-aware decoder can achieve a higher accuracy than the other state-of-the-art binary segmentation methods for these tasks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 56 of its 90 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

56 of 90 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  10. 2016Pyramid Scene Parsing Networkcited by 2,479
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
38 more
  1. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  3. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  4. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  5. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  6. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  7. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  8. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  9. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  10. 2018Context Encoding for Semantic Segmentationcited by 290
  11. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  12. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
  13. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  14. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 212
  15. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  16. 2021Concealed Object Detectioncited by 212
  17. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  18. 2014The Secrets of Salient Object Segmentationcited by 200
  19. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  20. 2016Deeply supervised salient object detection with short connectionscited by 196
  21. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  22. 2020Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Imagescited by 184
  23. 2014Object Detectors Emerge in Deep Scene CNNscited by 179
  24. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  25. 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
  26. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  27. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 141
  28. 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
  29. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  30. 2021Shallow Attention Network for Polyp Segmentationcited by 107
  31. 2021Mutual Graph Learning for Camouflaged Object Detectioncited by 103
  32. 2014Salient Object Detection: A Surveycited by 98
  33. 2021Context-aware Cross-level Fusion Network for Camouflaged Object Detectioncited by 86
  34. 2020Highly Efficient Salient Object Detection with 100K Parameterscited by 79
  35. 2021HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPScited by 71
  36. 2019FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentationcited by 70
  37. 2020Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contextscited by 51
  38. 2018Selectivity or Invariance: Boundary-aware Salient Object Detectioncited by 48

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 2.

6 papers.

  1. 2024Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagerycited by 30
  2. 2025BRISC: Annotated Dataset for Brain Tumor Segmentation and Classificationcited by 15
  3. 2023Building Extraction from Remote Sensing Images via an Uncertainty-Aware Networkcited by 8
  4. 2026DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidancecited by 6
  5. 2023Cross-level Attention with Overlapped Windows for Camouflaged Object Detectioncited by 2
  6. 2026BaT-SAM: Introducing Inductive Bias into SAM via a Mixture of Convolutional Experts for Brain Tumor Segmentationcited by 0