mlsanityData to 7 Oct 2026

Disentangled Feature Representation for Few-shot Image Classification

arXiv 2109.12548 ↗First posted 26 Sep 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain and style of the image samples. In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization tasks. We conducted extensive experiments to evaluate the proposed DFR on general and fine-grained few-shot classification, as well as few-shot domain generalization, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, CUB, as well as the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved the state-of-the-art results on all datasets.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 51 of its 88 references that are in the map. First posted on arXiv 26 Sep 2021.

Builds on

51 of 88 references.

References · 51

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2019A Closer Look at Few-shot Classificationcited by 679
38 more
  1. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  4. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  5. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  6. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  7. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  8. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  9. 2019Cross Attention Network for Few-shot Classificationcited by 218
  10. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  11. 2018Low-Shot Learning from Imaginary Datacited by 181
  12. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  13. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  14. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  15. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  16. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  17. 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 120
  18. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  19. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  20. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  21. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  22. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  23. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  24. 2020Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognitioncited by 69
  25. 2018Memory Matching Networks for One-Shot Image Recognitioncited by 65
  26. 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
  27. 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
  28. 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
  29. 2020Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognitioncited by 30
  30. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  31. 2020Variational Feature Disentangling for Fine-Grained Few-Shot Classificationcited by 26
  32. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  33. 2020Learning Disentangled Feature Representation for Hybrid-distorted Image Restorationcited by 21
  34. 2021Learning to Affiliate: Mutual Centralized Learning for Few-shot Classificationcited by 18
  35. 2020Disentangling 3D Prototypical Networks For Few-Shot Concept Learningcited by 15
  36. 2020Few-Shot Learning with Geometric Constraintscited by 13
  37. 2021Few-Shot and Continual Learning with Attentive Independent Mechanismscited by 13
  38. 2021Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classificationcited by 8

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 6; 2026: 1.

12 papers.

  1. 2022Disentangled Representation Learningcited by 111
  2. 2022Contributions of Shape, Texture, and Color in Visual Recognitioncited by 16
  3. 2025DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-IDcited by 11
  4. 2023Disentangled Representation Learning with Transmitted Information Bottleneckcited by 3
  5. 2025Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Datacited by 2
  6. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  7. 2024Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classificationcited by 1
  8. 2025A New Perspective On AI Safety Through Control Theory Methodologiescited by 1
  9. 2025CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglementcited by 1
  10. 2025Rethinking the Sample Relations for Few-Shot Classificationcited by 0
  11. 2025MCLRL: A Multi-Domain Contrastive Learning with Reinforcement Learning Framework for Few-Shot Modulation Recognitioncited by 0
  12. 2026Can One-Shot Test-Time Data Augmentation Help with Generalization?cited by 0