mlsanityData to 7 Oct 2026

Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning

arXiv 2112.10982 ↗First posted 21 Dec 2021cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes. While the current state-of-the-art approach is based on meta-learning, it performs poorly and saturates in learning after observing only a few shots. We propose the first fine-tuning solution, and demonstrate that it addresses the saturation problem while achieving state-of-the-art results on two datasets, PASCAL-5i and COCO-20i. We also show that it outperforms existing methods, whether fine-tuning multiple final layers or only the final layer. Finally, we present a triplet loss regularization that shows how to redistribute the balance of performance between novel and base categories so that there is a smaller gap between them.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

38 of 55 references.

References · 38

  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. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  12. 2017One-Shot Learning for Semantic Segmentationcited by 337
26 more
  1. 2019A Baseline for Few-Shot Image Classificationcited by 298
  2. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  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. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  6. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  7. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  8. 2015ParseNet: Looking Wider to See Bettercited by 176
  9. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  10. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  11. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  12. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  13. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  14. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  15. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  16. 2020Generalized Few-shot Semantic Segmentationcited by 59
  17. 2017Residual Conv-Deconv Grid Network for Semantic Segmentationcited by 57
  18. 2020Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Imagescited by 43
  19. 2019Revisiting Fine-tuning for Few-shot Learningcited by 29
  20. 2020SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentationcited by 27
  21. 2020Spatial Contrastive Learning for Few-Shot Classificationcited by 17
  22. 2021Few-Shot Segmentation with Global and Local Contrastive Learningcited by 17
  23. 2021Supervised Momentum Contrastive Learning for Few-Shot Classificationcited by 6
  24. 2020Few-Shot Image Classification via Contrastive Self-Supervised Learningcited by 5
  25. 2019The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentationcited by 4
  26. 2021SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypescited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2.

8 papers.

  1. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  2. 2022Prediction Calibration for Generalized Few-shot Semantic Segmentationcited by 16
  3. 2024Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Frameworkcited by 6
  4. 2023Few-shot 3D LiDAR Semantic Segmentation for Autonomous Drivingcited by 3
  5. 2025Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentationcited by 1
  6. 2023GMISeg: General Medical Image Segmentation without Re-Trainingcited by 0
  7. 2024Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditionscited by 0
  8. 2024TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentationcited by 0