mlsanityData to 14 Oct 2026

FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

arXiv 2208.10930 ↗First posted 23 Aug 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Conventional Few-shot classification (FSC) aims to recognize samples from novel classes given limited labeled data. Recently, domain generalization FSC (DG-FSC) has been proposed with the goal to recognize novel class samples from unseen domains. DG-FSC poses considerable challenges to many models due to the domain shift between base classes (used in training) and novel classes (encountered in evaluation). In this work, we make two novel contributions to tackle DG-FSC. Our first contribution is to propose Born-Again Network (BAN) episodic training and comprehensively investigate its effectiveness for DG-FSC. As a specific form of knowledge distillation, BAN has been shown to achieve improved generalization in conventional supervised classification with a closed-set setup. This improved generalization motivates us to study BAN for DG-FSC, and we show that BAN is promising to address the domain shift encountered in DG-FSC. Building on the encouraging findings, our second (major) contribution is to propose Few-Shot BAN (FS-BAN), a novel BAN approach for DG-FSC. Our proposed FS-BAN includes novel multi-task learning objectives: Mutual Regularization, Mismatched Teacher, and Meta-Control Temperature, each of these is specifically designed to overcome central and unique challenges in DG-FSC, namely overfitting and domain discrepancy. We analyze different design choices of these techniques. We conduct comprehensive quantitative and qualitative analysis and evaluation over six datasets and three baseline models. The results suggest that our proposed FS-BAN consistently improves the generalization performance of baseline models and achieves state-of-the-art accuracy for DG-FSC. Project Page: https://yunqing-me.github.io/Born-Again-FS/.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 52 of its 84 references that are in the map. First posted on arXiv 23 Aug 2022.

Builds on

52 of 84 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
38 more
  1. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  2. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  3. 2019A Closer Look at Few-shot Classificationcited by 684
  4. 2018Born Again Neural Networkscited by 546
  5. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  6. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  9. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  10. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  11. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  12. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  13. 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 359
  14. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  15. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  16. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  17. 2020Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learningcited by 297
  18. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  19. 2018DropBlock: A regularization method for convolutional networkscited by 262
  20. 2019Episodic Training for Domain Generalizationcited by 245
  21. 2019Cross Attention Network for Few-shot Classificationcited by 219
  22. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  23. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  24. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 96
  25. 2019BAM! Born-Again Multi-Task Networks for Natural Language Understandingcited by 85
  26. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  27. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  28. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  29. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  30. 2021Transferable Semantic Augmentation for Domain Adaptationcited by 56
  31. 2018Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Studentscited by 50
  32. 2022A Closer Look at Few-shot Image Generationcited by 49
  33. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  34. 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
  35. 2020Domain-Adaptive Few-Shot Learningcited by 40
  36. 2020Born-Again Tree Ensemblescited by 38
  37. 2018Private Model Compression via Knowledge Distillationcited by 37
  38. 2022Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?cited by 32

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 2.

9 papers.

  1. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  2. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  3. 2023Exploring Incompatible Knowledge Transfer in Few-shot Image Generationcited by 19
  4. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  5. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  6. 2023INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalizationcited by 4
  7. 2023ECEA: Extensible Co-Existing Attention for Few-Shot Object Detectioncited by 4
  8. 2023AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulationcited by 1
  9. 2022Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning
  2. 2023Diversified in-domain synthesis with efficient fine-tuning for few-shot classification
  3. 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
  4. 2026Learning to Curate What You Generate for Generalizable Few-Shot Class-Incremental Learning
  5. 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
  6. 2022On-Device Domain Generalization
  7. 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
  8. 2024FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization