mlsanityData to 14 Oct 2026

Simple Semantic-Aided Few-Shot Learning

arXiv 2311.18649 ↗First posted 30 Nov 2023cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Learning from a limited amount of data, namely Few-Shot Learning, stands out as a challenging computer vision task. Several works exploit semantics and design complicated semantic fusion mechanisms to compensate for rare representative features within restricted data. However, relying on naive semantics such as class names introduces biases due to their brevity, while acquiring extensive semantics from external knowledge takes a huge time and effort. This limitation severely constrains the potential of semantics in Few-Shot Learning. In this paper, we design an automatic way called Semantic Evolution to generate high-quality semantics. The incorporation of high-quality semantics alleviates the need for complex network structures and learning algorithms used in previous works. Hence, we employ a simple two-layer network termed Semantic Alignment Network to transform semantics and visual features into robust class prototypes with rich discriminative features for few-shot classification. The experimental results show our framework outperforms all previous methods on six benchmarks, demonstrating a simple network with high-quality semantics can beat intricate multi-modal modules on few-shot classification tasks. Code is available at https://github.com/zhangdoudou123/SemFew.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 43 of its 63 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

43 of 63 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2014Conditional Generative Adversarial Netscited by 2,162
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2016Learning to learn by gradient descent by gradient descentcited by 620
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
31 more
  1. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  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. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  9. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  10. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  11. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  12. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  13. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  14. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  15. 2019Improved Few-Shot Visual Classificationcited by 115
  16. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  17. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  18. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  19. 2019Meta-Learning of Neural Architectures for Few-Shot Learningcited by 73
  20. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  21. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  22. 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
  23. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
  24. 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
  25. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  26. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  27. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  28. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  29. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  30. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  31. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  2. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  3. 2026Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognitioncited by 4
  4. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  5. 2026DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learningcited by 2
  6. 2025Slot Attention-based Feature Filtering for Few-Shot Learningcited by 1
  7. 2026Rethinking the Good Enough Embedding for Easy Few-Shot Learningcited by 1
  8. 2025Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learningcited by 0
  9. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  10. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  11. 2025Stochastic-based Patch Filtering for Few-Shot Learningcited by 0
  12. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0
3 more
  1. 2026IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learningcited by 0
  2. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0
  3. 2026Uncertainty-DTW for Sequences and Visual Tokenscited by 0