mlsanityData to 7 Oct 2026

Mining Latent Classes for Few-shot Segmentation

arXiv 2103.15402 ↗First posted 29 Mar 2021cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel classes are treated as background during training phase. Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes. In our work, we propose a novel joint-training framework. Based on conventional episodic training on support-query pairs, we add an additional mining branch that exploits latent novel classes via transferable sub-clusters, and a new rectification technique on both background and foreground categories to enforce more stable prototypes. Over and above that, our transferable sub-cluster has the ability to leverage extra unlabeled data for further feature enhancement. Extensive experiments on two FSS benchmarks demonstrate that our method outperforms previous state-of-the-art by a large margin of 3.7% mIOU on PASCAL-5i and 7.0% mIOU on COCO-20i at the cost of 74% fewer parameters and 2.5x faster inference speed. The source code is available at https://github.com/LiheYoung/MiningFSS.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Builds on 50 of its 60 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

50 of 60 references.

References · 50

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
38 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  4. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  5. 2014How transferable are features in deep neural networks?cited by 1,216
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  8. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  9. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  11. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  12. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  13. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  14. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  15. 2017One-Shot Learning for Semantic Segmentationcited by 337
  16. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  17. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
  18. 2018Context Encoding for Semantic Segmentationcited by 289
  19. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  20. 2017Meta Networkscited by 268
  21. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  22. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  23. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  24. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  25. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  26. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  27. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  28. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  29. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  30. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  31. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  32. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  33. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  34. 2019Prototype Rectification for Few-Shot Learningcited by 96
  35. 2016One-shot Learning with Memory-Augmented Neural Networkscited by 60
  36. 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
  37. 2019Differentiable Meta-learning Model for Few-shot Semantic Segmentationcited by 31
  38. 2020Density-Aware Graph for Deep Semi-Supervised Visual Recognitioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 20; 2023: 21; 2024: 14; 2025: 7; 2026: 1.

69 papers.

Sort:

By area:

  1. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  2. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  3. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  4. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  5. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  6. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  7. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  8. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  9. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  10. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  11. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  12. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
38 more
  1. 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
  2. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  3. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  4. 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
  5. 2022Learning Local and Global Temporal Contexts for Video Semantic Segmentationcited by 24
  6. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  7. 2021Dense Gaussian Processes for Few-Shot Segmentationcited by 17
  8. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  9. 2024Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentationcited by 14
  10. 2024A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Modelscited by 13
  11. 2024CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspectionscited by 12
  12. 2024Robust Fast Adaptation from Adversarially Explicit Task Distribution Generationcited by 12
  13. 2025Not All Data Are Unlearned Equallycited by 12
  14. 2021MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learningcited by 10
  15. 2023Iterative Few-shot Semantic Segmentation from Image Label Textcited by 10
  16. 2023Exploring Open-Vocabulary Semantic Segmentation without Human Labelscited by 10
  17. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  18. 2022HM: Hybrid Masking for Few-Shot Segmentationcited by 9
  19. 2023Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentationcited by 9
  20. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
  21. 2022CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networkscited by 7
  22. 2022Cross-domain Few-shot Segmentation with Transductive Fine-tuningcited by 7
  23. 2021MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentationcited by 6
  24. 2022RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learningcited by 6
  25. 2023Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentationcited by 6
  26. 2024RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentationcited by 6
  27. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  28. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  29. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  30. 2023Towards Content-based Pixel Retrieval in Revisited Oxford and Pariscited by 5
  31. 2023DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptationcited by 5
  32. 2021End-to-end One-shot Human Parsingcited by 4
  33. 2024Boosting Few-Shot Semantic Segmentation Via Segment Anything Modelcited by 4
  34. 2023Few-shot Semantic Segmentation with Support-induced Graph Convolutional Networkcited by 3
  35. 2023Masked Cross-image Encoding for Few-shot Segmentationcited by 3
  36. 2023Self-Correlation and Cross-Correlation Learning for Few-Shot Remote Sensing Image Semantic Segmentationcited by 3
  37. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  38. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3

50 most cited of 69 All 69 (JSON)