mlsanityData to 14 Oct 2026

Class-relevant Patch Embedding Selection for Few-Shot Image Classification

arXiv 2405.03722 ↗First posted 6 May 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Effective image classification hinges on discerning relevant features from both foreground and background elements, with the foreground typically holding the critical information. While humans adeptly classify images with limited exposure, artificial neural networks often struggle with feature selection from rare samples. To address this challenge, we propose a novel method for selecting class-relevant patch embeddings. Our approach involves splitting support and query images into patches, encoding them using a pre-trained Vision Transformer (ViT) to obtain class embeddings and patch embeddings, respectively. Subsequently, we filter patch embeddings using class embeddings to retain only the class-relevant ones. For each image, we calculate the similarity between class embedding and each patch embedding, sort the similarity sequence in descending order, and only retain top-ranked patch embeddings. By prioritizing similarity between the class embedding and patch embeddings, we select top-ranked patch embeddings to be fused with class embedding to form a comprehensive image representation, enhancing pattern recognition across instances. Our strategy effectively mitigates the impact of class-irrelevant patch embeddings, yielding improved performance in pre-trained models. Extensive experiments on popular few-shot classification benchmarks demonstrate the simplicity, efficacy, and computational efficiency of our approach, outperforming state-of-the-art baselines under both 5-shot and 1-shot scenarios.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 40 of its 64 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

40 of 64 references.

References · 40

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  10. 2019A Closer Look at Few-shot Classificationcited by 684
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
28 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  3. 2018Meta-learning with differentiable closed-form solverscited by 397
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  6. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  7. 2019Cross Attention Network for Few-shot Classificationcited by 219
  8. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  9. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  10. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  11. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  12. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  13. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  14. 2021Relational Embedding for Few-Shot Classificationcited by 74
  15. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  16. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  17. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  18. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  19. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  20. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  21. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  22. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  23. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  24. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  25. 2020Mixture-based Feature Space Learning for Few-shot Image Classificationcited by 23
  26. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  27. 2021Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learningcited by 19
  28. 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Stochastic-based Patch Filtering for Few-Shot Learningcited by 0