mlsanityData to 7 Oct 2026

Improved Few-Shot Visual Classification

arXiv 1912.03432 ↗First posted 7 Dec 2019cs.CVcited by 114

Not on the map. Why?

Abstract (arXiv)

Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data. Most few-shot learning approaches to date have focused on progressively more complex neural feature extractors and classifier adaptation strategies, as well as the refinement of the task definition itself. In this paper, we explore the hypothesis that a simple class-covariance-based distance metric, namely the Mahalanobis distance, adopted into a state of the art few-shot learning approach (CNAPS) can, in and of itself, lead to a significant performance improvement. We also discover that it is possible to learn adaptive feature extractors that allow useful estimation of the high dimensional feature covariances required by this metric from surprisingly few samples. The result of our work is a new "Simple CNAPS" architecture which has up to 9.2% fewer trainable parameters than CNAPS and performs up to 6.1% better than state of the art on the standard few-shot image classification benchmark dataset.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 24; 2023: 28; 2024: 22; 2025: 13; 2026: 2.

114 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 162
  3. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  4. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 83
  5. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  6. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  7. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  8. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 52
  9. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  10. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  11. 2023A Closer Look at Few-shot Classification Againcited by 46
  12. 2023First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learningcited by 46
38 more
  1. 2021Property-Aware Relation Networks for Few-Shot Molecular Property Predictioncited by 41
  2. 2023The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classificationcited by 41
  3. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 40
  4. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  5. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  6. 2023Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalizationcited by 31
  7. 2022FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classificationcited by 26
  8. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  9. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  10. 2022Few-shot Learning with Noisy Labelscited by 23
  11. 2024AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learningcited by 22
  12. 2023Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real Worldcited by 18
  13. 2023Exploring Efficient Few-shot Adaptation for Vision Transformerscited by 16
  14. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  15. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  16. 2022AirFi: Empowering WiFi-based Passive Human Gesture Recognition to Unseen Environment via Domain Generalizationcited by 15
  17. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  18. 2024Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuningcited by 15
  19. 2025ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Modelscited by 15
  20. 2021Memory Efficient Meta-Learning with Large Imagescited by 14
  21. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  22. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  23. 2024Frozen Feature Augmentation for Few-Shot Image Classificationcited by 13
  24. 2023Cross-Modal Concept Learning and Inference for Vision-Language Modelscited by 12
  25. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  26. 2023Towards Task Sampler Learning for Meta-Learningcited by 11
  27. 2023Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensingcited by 11
  28. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  29. 2022Evidential Conditional Neural Processescited by 10
  30. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  31. 2023Learning to Drive Anywherecited by 9
  32. 2021Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classificationcited by 8
  33. 2021Task Affinity with Maximum Bipartite Matching in Few-Shot Learningcited by 8
  34. 2024Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognitioncited by 8
  35. 2021Prototype Completion for Few-Shot Learningcited by 7
  36. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  37. 2023MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classificationcited by 7
  38. 2023In-Context Learning for Few-Shot Molecular Property Predictioncited by 7

50 most cited of 114 All 114 (JSON)