mlsanityData to 7 Oct 2026

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

arXiv 2104.01893 ↗First posted 5 Apr 2021cs.CVcited by 207

Not on the map. Why?

Abstract (arXiv)

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.

Key facts. Cited by 207 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

30 of 44 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  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. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  12. 2018Dual Attention Network for Scene Segmentationcited by 1,001
18 more
  1. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  2. 2017One-Shot Learning for Semantic Segmentationcited by 337
  3. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  4. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  5. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  6. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  7. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  8. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  9. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  10. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  11. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  12. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  13. 2018Superpixel Sampling Networkscited by 79
  14. 2019ACFNet: Attentional Class Feature Network for Semantic Segmentationcited by 75
  15. 2020Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networkscited by 70
  16. 2016Superpixels: An Evaluation of the State-of-the-Artcited by 52
  17. 2020BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentationcited by 28
  18. 2020SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentationcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 40; 2023: 49; 2024: 52; 2025: 34; 2026: 11.

207 papers.

Sort:

By area:

  1. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  2. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  3. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  4. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  5. 2024D4M: Dataset Distillation via Disentangled Diffusion Modelcited by 76
  6. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  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. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  12. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
38 more
  1. 2023Exploring Effective Factors for Improving Visual In-Context Learningcited by 43
  2. 2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
  3. 2021One-Shot Object Affordance Detection in the Wildcited by 40
  4. 2023Continual Semantic Segmentation with Automatic Memory Sample Selectioncited by 39
  5. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  6. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  7. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  8. 2022Few-shot Medical Image Segmentation with Cycle-resemblance Attentioncited by 33
  9. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  10. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  11. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  12. 2022Unsupervised Video Object Segmentation via Prototype Memory Networkcited by 30
  13. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  14. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  15. 2022Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networkscited by 28
  16. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  17. 2024PTaRL: Prototype-based Tabular Representation Learning via Space Calibrationcited by 27
  18. 2022SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detectioncited by 26
  19. 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
  20. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  21. 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
  22. 2021All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-supervised Medical Image Segmentationcited by 24
  23. 2022Learning Local and Global Temporal Contexts for Video Semantic Segmentationcited by 24
  24. 2023Neuralizer: General Neuroimage Analysis without Re-Trainingcited by 24
  25. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  26. 2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
  27. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  28. 2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
  29. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  30. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  31. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
  32. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  33. 2023MP-FedCL: Multiprototype Federated Contrastive Learning for Edge Intelligencecited by 20
  34. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  35. 2023What Can Human Sketches Do for Object Detection?cited by 19
  36. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  37. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  38. 2022MSI: Maximize Support-Set Information for Few-Shot Segmentationcited by 18

50 most cited of 207 All 207 (JSON)