mlsanityData to 7 Oct 2026

Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation

arXiv 1603.06098 ↗First posted 19 Mar 2016cs.CVcited by 198

Not on the map. Why?

Abstract (arXiv)

We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries. We show experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset. We furthermore give insight into the working mechanism of our method by a detailed experimental study that illustrates how the segmentation quality is affected by each term of the proposed loss function as well as their combinations.

Key facts. Cited by 198 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 52; 2022: 55; 2023: 42; 2024: 31; 2025: 11; 2026: 7.

198 papers.

Sort:

By area:

  1. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  2. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  3. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  4. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  5. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  6. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  7. 2021Large-scale Unsupervised Semantic Segmentationcited by 98
  8. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  9. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  10. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  11. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  12. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
38 more
  1. 2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
  2. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  3. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  4. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  5. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
  6. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  7. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  8. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  9. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  10. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  11. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  12. 2021Pseudo-mask Matters in Weakly-supervised Semantic Segmentationcited by 48
  13. 2021ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenescited by 47
  14. 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
  15. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  16. 2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
  17. 2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
  18. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  19. 2023CLIP in Medical Imaging: A Surveycited by 40
  20. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  21. 2022Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformerscited by 39
  22. 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
  23. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37
  24. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  25. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 30
  26. 2023Extracting Class Activation Maps from Non-Discriminative Features as wellcited by 30
  27. 2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
  28. 2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 28
  29. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
  30. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  31. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  32. 2023Shatter and Gather: Learning Referring Image Segmentation with Text Supervisioncited by 25
  33. 2021Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examplescited by 24
  34. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  35. 2021Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentationcited by 22
  36. 2022From colouring-in to pointillism: revisiting semantic segmentation supervisioncited by 22
  37. 2023WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentationcited by 22
  38. 2023MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentationcited by 22

50 most cited of 198 All 198 (JSON)