mlsanityData to 14 Oct 2026

Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning

arXiv 2309.02833 ↗First posted 6 Sep 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

While many FSCIL studies have been undertaken, achieving satisfactory performance, especially during incremental sessions, has remained challenging. One prominent challenge is that the encoder, trained with an ample base session training set, often underperforms in incremental sessions. In this study, we introduce a novel training framework for FSCIL, capitalizing on the generalizability of the Contrastive Language-Image Pre-training (CLIP) model to unseen classes. We achieve this by formulating image-object-specific (IOS) classifiers for the input images. Here, an IOS classifier refers to one that targets specific attributes (like wings or wheels) of class objects rather than the image's background. To create these IOS classifiers, we encode a bias prompt into the classifiers using our specially designed module, which harnesses key-prompt pairs to pinpoint the IOS features of classes in each session. From an FSCIL standpoint, our framework is structured to retain previous knowledge and swiftly adapt to new sessions without forgetting or overfitting. This considers the updatability of modules in each session and some tricks empirically found for fast convergence. Our approach consistently demonstrates superior performance compared to state-of-the-art methods across the miniImageNet, CIFAR100, and CUB200 datasets. Further, we provide additional experiments to validate our learned model's ability to achieve IOS classifiers. We also conduct ablation studies to analyze the impact of each module within the architecture.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 6 Sep 2023.

Builds on

29 of 34 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  6. 2016An overview of gradient descent optimization algorithmscited by 1,033
  7. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  8. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  9. 2020Few-Shot Class-Incremental Learningcited by 251
  10. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  11. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  12. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 115
17 more
  1. 2022Constrained Few-shot Class-incremental Learningcited by 94
  2. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  3. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 84
  4. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  5. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 72
  6. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  7. 2023Introducing Language Guidance in Prompt-based Continual Learningcited by 49
  8. 2023AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learningcited by 46
  9. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  10. 2023When Prompt-based Incremental Learning Does Not Meet Strong Pretrainingcited by 41
  11. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  12. 2023Multimodal Parameter-Efficient Few-Shot Class Incremental Learningcited by 19
  13. 2023CoPL: Contextual Prompt Learning for Vision-Language Understandingcited by 10
  14. 2023Semantic-visual Guided Transformer for Few-shot Class-incremental Learningcited by 6
  15. 2023Multi-View Class Incremental Learningcited by 5
  16. 2023Balanced Supervised Contrastive Learning for Few-Shot Class-Incremental Learningcited by 1
  17. 2023MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  2. 2025Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learningcited by 8
  3. 2024A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasetscited by 4
  4. 2024PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learningcited by 1