mlsanityData to 7 Oct 2026

Self-Support Few-Shot Semantic Segmentation

arXiv 2207.11549 ↗First posted 23 Jul 2022cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

Existing few-shot segmentation methods have achieved great progress based on the support-query matching framework. But they still heavily suffer from the limited coverage of intra-class variations from the few-shot supports provided. Motivated by the simple Gestalt principle that pixels belonging to the same object are more similar than those to different objects of same class, we propose a novel self-support matching strategy to alleviate this problem, which uses query prototypes to match query features, where the query prototypes are collected from high-confidence query predictions. This strategy can effectively capture the consistent underlying characteristics of the query objects, and thus fittingly match query features. We also propose an adaptive self-support background prototype generation module and self-support loss to further facilitate the self-support matching procedure. Our self-support network substantially improves the prototype quality, benefits more improvement from stronger backbones and more supports, and achieves SOTA on multiple datasets. Codes are at urlhttps://github.com/fanq15/SSP.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 72 of its 96 references that are in the map. First posted on arXiv 23 Jul 2022.

Builds on

72 of 96 references.

References · 72

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2018Dual Attention Network for Scene Segmentationcited by 1,001
38 more
  1. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  2. 2019A Closer Look at Few-shot Classificationcited by 679
  3. 2019Panoptic Feature Pyramid Networkscited by 644
  4. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  5. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  6. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2018Meta-learning with differentiable closed-form solverscited by 395
  10. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  11. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  12. 2017One-Shot Learning for Semantic Segmentationcited by 337
  13. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  14. 2018How to train your MAMLcited by 306
  15. 2019A Baseline for Few-Shot Image Classificationcited by 298
  16. 2017Dilated Residual Networkscited by 293
  17. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  18. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  19. 2019Cross Attention Network for Few-shot Classificationcited by 218
  20. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  21. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  22. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  23. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  24. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  25. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  26. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  27. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  28. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  29. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  30. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  31. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  32. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  33. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  34. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  35. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  36. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  37. 2019Large-scale interactive object segmentation with human annotatorscited by 109
  38. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 33; 2024: 24; 2025: 21; 2026: 15.

96 papers.

Sort:

By area:

  1. 2023SegGPT: Segmenting Everything In Contextcited by 193
  2. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  3. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  4. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  5. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  6. 2023Exploring Effective Factors for Improving Visual In-Context Learningcited by 43
  7. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  8. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  9. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  10. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  11. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29
  12. 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
38 more
  1. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  2. 2023Multi-Modal Prototypes for Open-World Semantic Segmentationcited by 22
  3. 2023UniRef++: Segment Every Reference Object in Spatial and Temporal Spacescited by 22
  4. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  5. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  6. 2023Few Shot Medical Image Segmentation with Cross Attention Transformercited by 19
  7. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  8. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  9. 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
  10. 2024Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentationcited by 14
  11. 2023Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentationcited by 13
  12. 2024Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformationcited by 13
  13. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  14. 2024CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspectionscited by 12
  15. 2024Query-guided Prototype Evolution Network for Few-Shot Segmentationcited by 12
  16. 2025Not All Data Are Unlearned Equallycited by 12
  17. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  18. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  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. 2024BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAMcited by 8
  22. 2025The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentationcited by 8
  23. 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentationcited by 8
  24. 2023Few-Shot Rotation-Invariant Aerial Image Semantic Segmentationcited by 7
  25. 2025Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentationcited by 7
  26. 2022Prototype as Query for Few Shot Semantic Segmentationcited by 6
  27. 2023Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samplescited by 6
  28. 2023Stable Segment Anything Modelcited by 6
  29. 2024Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentationcited by 6
  30. 2024RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentationcited by 6
  31. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  32. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  33. 2023Towards Content-based Pixel Retrieval in Revisited Oxford and Pariscited by 5
  34. 2023DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptationcited by 5
  35. 2023ECEA: Extensible Co-Existing Attention for Few-Shot Object Detectioncited by 4
  36. 2025Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Modelscited by 4
  37. 2025Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retrainingcited by 4
  38. 2023Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentationcited by 3

50 most cited of 96 All 96 (JSON)