mlsanityData to 7 Oct 2026

Can One-Shot Test-Time Data Augmentation Help with Generalization?

arXiv 2602.00114 ↗First posted 27 Jan 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Data augmentation is crucial for model generalization, but existing methods are mostly centered on the training stage. Test-time augmentation, while underexplored, can be practically effective for generalization while avoiding extra model parameters or fine-tuning. Given the increasing training cost and the literature gap, we study whether it is possible to perform effective test-time augmentation using image generation from just the single original image. We first analyze the importance of test-time augmentation, and then design and study a simple yet natural operator named 1S-DAug, which comprises geometric perturbations with controlled noise injection and image-conditioned denoising. We obtain positive results on well-established image-classification benchmarks across four datasets and multiple models, achieving up to 20% relative accuracy improvement without model training or parameter access. Code will be released.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 61 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

52 of 61 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  7. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  10. 2023Visual Instruction Tuningcited by 7,792
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
38 more
  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  10. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  11. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  12. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  13. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  14. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  15. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  16. 2019A Closer Look at Few-shot Classificationcited by 679
  17. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
  18. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 468
  19. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  20. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  21. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  22. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  23. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  24. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  25. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  26. 2023Effective Data Augmentation With Diffusion Modelscited by 282
  27. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  28. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  29. 2018Low-Shot Learning from Imaginary Datacited by 181
  30. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  31. 2020Laplacian Regularized Few-Shot Learningcited by 90
  32. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  33. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  34. 2020Transductive Information Maximization For Few-Shot Learningcited by 44
  35. 2020Data Augmentation for Meta-Learningcited by 38
  36. 2023One-shot Unsupervised Domain Adaptation with Personalized Diffusion Modelscited by 35
  37. 2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
  38. 2022CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPUcited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.