mlsanityData to 7 Oct 2026

Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation

arXiv 2210.16829 ↗First posted 30 Oct 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to perform segmentation with just a few annotated examples. In this work, we tackle the few-shot segmentation using a self-regularized prototypical network (SRPNet) based on prototype extraction for better utilization of the support information. The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation masks for query images by a distance metric - the fidelity. A direct yet effective prototype regularization on support set is proposed in SRPNet, in which the generated prototypes are evaluated and regularized on the support set itself. The extent to which the generated prototypes restore the support mask imposes an upper limit on performance. The performance on the query set should never exceed the upper limit no matter how complete the knowledge is generalized from support set to query set. With the specific prototype regularization, SRPNet fully exploits knowledge from the support and offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. The query performance is further improved by an iterative query inference (IQI) module that combines a set of regularized prototypes. Our proposed SRPNet achieves new state-of-art performance on 1-shot and 5-shot segmentation benchmarks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

39 of 61 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  10. 2015Recent Advances in Convolutional Neural Networkscited by 360
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2017Few-Shot Learning with Graph Neural Networkscited by 324
27 more
  1. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  2. 2021Vision-Language Transformer and Query Generation for Referring Segmentationcited by 239
  3. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  4. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  5. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  6. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  7. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  8. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  9. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  10. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 110
  11. 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
  12. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  13. 2019Prototype Rectification for Few-Shot Learningcited by 96
  14. 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
  15. 2019Semantic Correlation Promoted Shape-Variant Context for Segmentationcited by 61
  16. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  17. 2022Instance-Specific Feature Propagation for Referring Segmentationcited by 45
  18. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  19. 2022Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningcited by 33
  20. 2019Feature Boosting Network For 3D Pose Estimationcited by 26
  21. 2021Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learningcited by 19
  22. 2021Few-Shot Segmentation with Global and Local Contrastive Learningcited by 17
  23. 2020Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentationcited by 15
  24. 2021Towards Enhancing Fine-grained Details for Image Mattingcited by 12
  25. 2021Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognitioncited by 12
  26. 2021M2IOSR: Maximal Mutual Information Open Set Recognitioncited by 12
  27. 2018A Deep One-Shot Network for Query-based Logo Retrievalcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 5; 2025: 3.

12 papers.

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  2. 2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
  3. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  4. 2023GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learningcited by 7
  5. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  6. 2024Boosting Few-Shot Semantic Segmentation Via Segment Anything Modelcited by 4
  7. 2023Few-shot 3D LiDAR Semantic Segmentation for Autonomous Drivingcited by 3
  8. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
  9. 2025Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Modelscited by 2
  10. 2024LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentationcited by 1
  11. 2025Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Designcited by 0
  12. 2025DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Modelcited by 0