mlsanityData to 14 Oct 2026

Generating Representative Samples for Few-Shot Classification

arXiv 2205.02918 ↗First posted 5 May 2022cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual samples based on semantic embeddings using a conditional variational autoencoder (CVAE) model. We train this CVAE model on base classes and use it to generate features for novel classes. More importantly, we guide this VAE to strictly generate representative samples by removing non-representative samples from the base training set when training the CVAE model. We show that this training scheme enhances the representativeness of the generated samples and therefore, improves the few-shot classification results. Experimental results show that our method improves three FSL baseline methods by substantial margins, achieving state-of-the-art few-shot classification performance on miniImageNet and tieredImageNet datasets for both 1-shot and 5-shot settings. Code is available at: https://github.com/cvlab-stonybrook/fsl-rsvae.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 69 of its 93 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

69 of 93 references.

References · 69

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  10. 2019A Closer Look at Few-shot Classificationcited by 684
  11. 2017Unsupervised Image-to-Image Translation Networkscited by 603
  12. 2019Meta-Learning with Implicit Gradientscited by 525
38 more
  1. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  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 437
  5. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  6. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  7. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  8. 2017Data Augmentation Generative Adversarial Networkscited by 278
  9. 2019Cross Attention Network for Few-shot Classificationcited by 219
  10. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  11. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  12. 2018Low-Shot Learning from Imaginary Datacited by 181
  13. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  14. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  15. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  16. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  17. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  18. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  19. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  20. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  21. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  22. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  23. 2017A Tutorial on Kernel Density Estimation and Recent Advancescited by 101
  24. 2019Shadow Removal via Shadow Image Decompositioncited by 98
  25. 2019Prototype Rectification for Few-Shot Learningcited by 97
  26. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  27. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  28. 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
  29. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  30. 2015Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptionscited by 64
  31. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  32. 2020From Shadow Segmentation to Shadow Removalcited by 59
  33. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  34. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  35. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  36. 2019Video Generation from Single Semantic Label Mapcited by 54
  37. 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
  38. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 12; 2024: 10; 2025: 9; 2026: 4.

39 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 79
  3. 2023Zero-shot Object Countingcited by 57
  4. 2023Norm-guided latent space exploration for text-to-image generationcited by 43
  5. 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
  6. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  7. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  8. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  9. 2024Assessing Sample Quality via the Latent Space of Generative Modelscited by 8
  10. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  11. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  12. 2023Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptationcited by 6
27 more
  1. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  2. 2025Few-shot Personalized Scanpath Predictioncited by 5
  3. 2026Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognitioncited by 4
  4. 2023Disentangled Representation Learning with Transmitted Information Bottleneckcited by 3
  5. 2024Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Densitycited by 3
  6. 2025VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Modelscited by 3
  7. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  8. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  9. 2024Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentationcited by 2
  10. 2026DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learningcited by 2
  11. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  12. 2023Trustworthy Representation Learning Across Domainscited by 1
  13. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  14. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  15. 2024Knowledge Adaptation Network for Few-Shot Class-Incremental Learningcited by 1
  16. 2025CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentationcited by 1
  17. 2026GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Taskcited by 1
  18. 2023Knowledge Transfer-Driven Few-Shot Class-Incremental Learningcited by 0
  19. 2023Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learningcited by 0
  20. 2024Meta Episodic learning with Dynamic Task Sampling for CLIP-based Point Cloud Classificationcited by 0
  21. 2024A Feature Generator for Few-Shot Learningcited by 0
  22. 2025Constraint Multi-class Positive and Unlabeled Learning for Distantly Supervised Named Entity Recognitioncited by 0
  23. 2025CoCoDiff: Diversifying Skeleton Action Features via Coarse-Fine Text-Co-Guided Latent Diffusioncited by 0
  24. 2025Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Carecited by 0
  25. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  26. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  27. 2026MT-ProtBERT: Multi-task Learning ProtBERT for Intrinsically Disordered Proteins Classification with Scarce Datacited by 0