mlsanityData to 14 Oct 2026

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

arXiv 2211.14126 ↗First posted 25 Nov 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-5i and COCO-20i. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-5i) and from 3% to 12% (COCO-20i) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

31 of 40 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2016Learning without Forgettingcited by 2,496
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2018End-to-End Incremental Learningcited by 597
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2017One-Shot Learning for Semantic Segmentationcited by 337
  10. 2019A Baseline for Few-Shot Image Classificationcited by 298
  11. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  12. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
19 more
  1. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  2. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  3. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 190
  4. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  5. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  6. 2014Simultaneous Detection and Segmentationcited by 159
  7. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  8. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  9. 2022Federated Class-Incremental Learningcited by 127
  10. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  11. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  12. 2020Laplacian Regularized Few-Shot Learningcited by 92
  13. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  14. 2020Generalized Few-shot Semantic Segmentationcited by 59
  15. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  16. 2018Deep clustering: On the link between discriminative models and K-meanscited by 37
  17. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  18. 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
  19. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 8; 2026: 5.

22 papers.

Sort:

By area:

  1. 2023Multi-Modal Prototypes for Open-World Semantic Segmentationcited by 22
  2. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  3. 2024Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approachcited by 15
  4. 2024Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentationcited by 13
  5. 2024Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Frameworkcited by 6
  6. 2025Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Modelcited by 5
  7. 2025The Power of One: A Single Example is All it Takes for Segmentation in VLMscited by 4
  8. 2024Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentationcited by 3
  9. 2024Class Similarity Transition: Decoupling Class Similarities and Imbalance from Generalized Few-shot Segmentationcited by 3
  10. 2024Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domaincited by 3
  11. 2024Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmarkcited by 3
  12. 2025Test-Time Discovery via Hashing Memorycited by 3
10 more
  1. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  2. 2025Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentationcited by 1
  3. 2025Personalized OVSS: Understanding Personal Concept in Open-Vocabulary Semantic Segmentationcited by 1
  4. 2026Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentationcited by 1
  5. 2026Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentationcited by 1
  6. 2024Applying ViT in Generalized Few-shot Semantic Segmentationcited by 0
  7. 2025Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentationcited by 0
  8. 2026Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbationscited by 0
  9. 2026Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?cited by 0
  10. 2026Information Maximization for Long-Tailed Semi-Supervised Domain Generalizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Iterative Few-shot Semantic Segmentation from Image Label Text
  2. 2023Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation
  3. 2024Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
  4. 2023Language-guided Few-shot Semantic Segmentation
  5. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentation
  6. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation
  7. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
  8. 2023A Simple Recipe for Language-guided Domain Generalized Segmentation