mlsanityData to 7 Oct 2026

Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning

arXiv 2507.09183 ↗First posted 12 Jul 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Few-Shot Class-Incremental Learning (FSCIL) faces dual challenges of data scarcity and incremental learning in real-world scenarios. While pool-based prompting methods have demonstrated success in traditional incremental learning, their effectiveness in FSCIL settings remains unexplored. This paper presents the first study of current prompt pool methods in FSCIL tasks, revealing an unanticipated performance degradation in incremental sessions. Through comprehensive analysis, we identify that this phenomenon stems from token-dimension saturation: with limited data, excessive prompts compete for task-relevant information, leading to model overfitting. Based on this finding, we propose LGSP-Prompt (Local-Global Spatial Prompting), which innovatively shifts pool-based prompt learning from the token dimension to the spatial dimension. LGSP-Prompt generates spatial prompts by synergistically combining local spatial features and global frequency-domain representations to highlight key patterns in input images. We construct two spatial prompt pools enabling dynamic prompt selection to maintain acquired knowledge while effectively learning novel sessions. Extensive experiments demonstrate that our approach achieves state-of-the-art performance across multiple FSCIL benchmarks, showing significant advantages in both base knowledge preservation and incremental learning. Our implementation is available at https://github.com/Jywsuperman/LGSP.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 12 Jul 2025.

Builds on

49 of 64 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  9. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  10. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  11. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  12. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
37 more
  1. 2020Few-Shot Class-Incremental Learningcited by 249
  2. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  3. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  4. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  5. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  6. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  7. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  8. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  9. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  10. 2022Constrained Few-shot Class-incremental Learningcited by 93
  11. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  12. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  13. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
  14. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  15. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  16. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
  17. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  18. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  19. 2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
  20. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  21. 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learnerscited by 35
  22. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  23. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  24. 2023Multimodal Parameter-Efficient Few-Shot Class Incremental Learningcited by 19
  25. 2024Compositional Few-Shot Class-Incremental Learningcited by 18
  26. 2023Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learningcited by 16
  27. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  28. 2024Rethinking Few-shot Class-incremental Learning: Learning from Yourselfcited by 13
  29. 2024Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learningcited by 12
  30. 2021Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learningcited by 11
  31. 2024Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learningcited by 9
  32. 2024Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learningcited by 5
  33. 2023Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learningcited by 4
  34. 2024Enhanced Few-Shot Class-Incremental Learning via Ensemble Modelscited by 4
  35. 2024A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasetscited by 4
  36. 2024PViT: Prior-augmented Vision Transformer for Out-of-distribution Detectioncited by 3
  37. 2023Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Fillingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learningcited by 5
  2. 2026Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignmentcited by 4
  3. 2026Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detectioncited by 2
  4. 2026Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environmentscited by 2
  5. 2025Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusioncited by 0
  6. 2026CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Promptscited by 0
  7. 2026Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learningcited by 0
  8. 2026Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detectioncited by 0