mlsanityData to 7 Oct 2026

Integrative Few-Shot Learning for Classification and Segmentation

arXiv 2203.15712 ↗First posted 29 Mar 2022cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 72 of its 104 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

72 of 104 references.

References · 72

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  3. 2017Non-local Neural Networkscited by 2,290
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  6. 2018Group Normalizationcited by 1,514
  7. 2019A Closer Look at Few-shot Classificationcited by 679
  8. 2018End-to-End Incremental Learningcited by 596
  9. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  12. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  13. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  14. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  15. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  16. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  17. 2018Meta-learning with differentiable closed-form solverscited by 395
  18. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  19. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  20. 2017One-Shot Learning for Semantic Segmentationcited by 337
  21. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  22. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  23. 2019A Baseline for Few-Shot Image Classificationcited by 298
  24. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  25. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  26. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  27. 2019Cross Attention Network for Few-shot Classificationcited by 218
  28. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  29. 2019Local Relation Networks for Image Recognitioncited by 210
  30. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  31. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  32. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  33. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  34. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  35. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  36. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  37. 2020General Multi-label Image Classification with Transformerscited by 126
  38. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 11; 2025: 2; 2026: 1.

25 papers.

Sort:

By area:

  1. 2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
  2. 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
  3. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  4. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  5. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  6. 2022MSI: Maximize Support-Set Information for Few-Shot Segmentationcited by 18
  7. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  8. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  9. 2024Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Promptscited by 9
  10. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
  11. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  12. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
13 more
  1. 2023A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentationcited by 3
  2. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  3. 2022Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentationcited by 2
  4. 2023Few-Shot Classification & Segmentation Using Large Language Models Agentcited by 2
  5. 2024Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Modelscited by 2
  6. 2024Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentationcited by 2
  7. 2023Target-aware Bi-Transformer for Few-shot Segmentationcited by 0
  8. 2024Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentationcited by 0
  9. 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registrationcited by 0
  10. 2024FCC: Fully Connected Correlation for One-Shot Segmentationcited by 0
  11. 2025FSSUWNet: Mitigating the Fragility of Pre-trained Models with Feature Enhancement for Few-Shot Semantic Segmentation in Underwater Imagescited by 0
  12. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0
  13. 2026Gromov Wasserstein Optimal Transport for Semantic Correspondencescited by 0