mlsanityData to 14 Oct 2026

CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation

arXiv 1811.10842 ↗First posted 27 Nov 2018cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplementary representations can be propagated to obtain more consistent and integral regions. To leverage this information, we propose an end-to-end cross-image affinity module, which exploits pixel-level cross-image relationships with only image-level labels. By means of this, our approach achieves 64.3% and 65.3% mIoU on Pascal VOC 2012 validation and test set respectively, which is a new state-of-the-art result by only using image-level labels for weakly supervised semantic segmentation, demonstrating the superiority of our approach.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 23; 2023: 18; 2024: 13; 2025: 3; 2026: 1.

80 papers.

Sort:

  1. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  2. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  3. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  4. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  5. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  6. 2021Large-scale Unsupervised Semantic Segmentationcited by 101
  7. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  8. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  9. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  10. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  11. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
  12. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
38 more
  1. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  2. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  3. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  4. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  5. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  6. 2021Weakly Supervised Temporal Adjacent Network for Language Groundingcited by 37
  7. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37
  8. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  9. 2023Foundation Model Assisted Weakly Supervised Semantic Segmentationcited by 33
  10. 2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
  11. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
  12. 2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
  13. 2021Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentationcited by 22
  14. 2023MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentationcited by 22
  15. 2022Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentationcited by 21
  16. 2022Pointly-Supervised Panoptic Segmentationcited by 21
  17. 2021Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspacecited by 19
  18. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19
  19. 2023Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Modelscited by 19
  20. 2024Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentationcited by 16
  21. 2022Weakly Supervised Semantic Segmentation via Progressive Patch Learningcited by 15
  22. 2024Adaptive Patch Contrast for Weakly Supervised Semantic Segmentationcited by 15
  23. 2021Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentationcited by 13
  24. 2023MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentationcited by 13
  25. 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
  26. 2022Self-Supervised Equivariant Regularization Reconciles Multiple Instance Learning: Joint Referable Diabetic Retinopathy Classification and Lesion Segmentationcited by 10
  27. 2021Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentationcited by 9
  28. 2022Bagging Regional Classification Activation Maps for Weakly Supervised Object Localizationcited by 9
  29. 2021GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentationcited by 8
  30. 2023Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentationcited by 8
  31. 2024Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentationcited by 8
  32. 2022Exploiting Shape Cues for Weakly Supervised Semantic Segmentationcited by 6
  33. 2021Towards Single Stage Weakly Supervised Semantic Segmentationcited by 5
  34. 2021Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentationcited by 5
  35. 2021Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Cloudscited by 4
  36. 2021SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Costcited by 4
  37. 2024Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentationcited by 4
  38. 2024Fine-grained Background Representation for Weakly Supervised Semantic Segmentationcited by 4

50 most cited of 80 All 80 (JSON)