mlsanityData to 7 Oct 2026

Single-Stage Semantic Segmentation from Image Labels

arXiv 2005.08104 ↗First posted 16 May 2020cs.CV cs.LGcited by 167

Not on the map. Why?

Abstract (arXiv)

Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model complexity and sophisticated multi-stage training procedures. This is in contrast to earlier work that used only a single stage - training one segmentation network on image labels - which was abandoned due to inferior segmentation accuracy. In this work, we first define three desirable properties of a weakly supervised method: local consistency, semantic fidelity, and completeness. Using these properties as guidelines, we then develop a segmentation-based network model and a self-supervised training scheme to train for semantic masks from image-level annotations in a single stage. We show that despite its simplicity, our method achieves results that are competitive with significantly more complex pipelines, substantially outperforming earlier single-stage methods.

Key facts. Cited by 167 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 21; 2023: 36; 2024: 43; 2025: 30; 2026: 14.

167 papers.

Sort:

By area:

  1. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 169
  2. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  3. 2022Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairscited by 130
  4. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  5. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  6. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  7. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
  8. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  9. 2024Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentationcited by 76
  10. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  11. 2023CLIP as RNN: Segment Countless Visual Concepts without Training Endeavorcited by 69
  12. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
38 more
  1. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  2. 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 64
  3. 2023Diffusion Models for Open-Vocabulary Segmentationcited by 63
  4. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  5. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  6. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  7. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  8. 2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
  9. 2024Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generationcited by 43
  10. 2024EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Modelscited by 42
  11. 2024Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentationcited by 42
  12. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  13. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  14. 2023CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Freecited by 39
  15. 2024Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentationcited by 38
  16. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37
  17. 2023Referring Image Segmentation Using Text Supervisioncited by 35
  18. 2023Foundation Model Assisted Weakly Supervised Semantic Segmentationcited by 31
  19. 2024ResCLIP: Residual Attention for Training-free Dense Vision-language Inferencecited by 28
  20. 2021MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detectioncited by 27
  21. 2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
  22. 2023Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentationcited by 26
  23. 2024DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cutcited by 26
  24. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  25. 2021Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examplescited by 24
  26. 2023LEOD: Label-Efficient Object Detection for Event Camerascited by 24
  27. 2021Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentationcited by 23
  28. 2023Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learningcited by 23
  29. 2024Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentationcited by 23
  30. 2021Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentationcited by 22
  31. 2023MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentationcited by 22
  32. 2022Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentationcited by 21
  33. 2022Weakly-supervised segmentation of referring expressionscited by 21
  34. 2023Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentationcited by 21
  35. 2024Image-Text Co-Decomposition for Text-Supervised Semantic Segmentationcited by 21
  36. 2025LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentationcited by 21
  37. 2021Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspacecited by 19
  38. 2022Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Poolingcited by 19

50 most cited of 167 All 167 (JSON)