mlsanityData to 7 Oct 2026

DETA: Denoised Task Adaptation for Few-Shot Learning

arXiv 2303.06315 ↗First posted 11 Mar 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on developing advanced algorithms to achieve the goal, while neglecting the inherent problems of the given support samples. In fact, with only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified. To address this challenge, in this work we propose DEnoised Task Adaptation (DETA), a first, unified image- and label-denoising framework orthogonal to existing task adaptation approaches. Without extra supervision, DETA filters out task-irrelevant, noisy representations by taking advantage of both global visual information and local region details of support samples. On the challenging Meta-Dataset, DETA consistently improves the performance of a broad spectrum of baseline methods applied on various pre-trained models. Notably, by tackling the overlooked image noise in Meta-Dataset, DETA establishes new state-of-the-art results. Code is released at https://github.com/JimZAI/DETA.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 11 Mar 2023.

Builds on

53 of 66 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  11. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  12. 2017A Closer Look at Memorization in Deep Networkscited by 936
38 more
  1. 2019A Closer Look at Few-shot Classificationcited by 679
  2. 2021Transformer in Transformercited by 632
  3. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  4. 2018Do Better ImageNet Models Transfer Better?cited by 560
  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 377
  7. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  8. 2019A Baseline for Few-Shot Image Classificationcited by 298
  9. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  10. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  11. 2019Cross Attention Network for Few-shot Classificationcited by 218
  12. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  13. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  14. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  15. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  16. 2019Improved Few-Shot Visual Classificationcited by 114
  17. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  18. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  19. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  20. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  21. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  22. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  23. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  24. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  25. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  26. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  27. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  28. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  29. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  30. 2023A Closer Look at Few-shot Classification Againcited by 46
  31. 2020Enhancing Few-Shot Image Classification with Unlabelled Examplescited by 32
  32. 2019PARN: Position-Aware Relation Networks for Few-Shot Learningcited by 27
  33. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  34. 2020Optimized Generic Feature Learning for Few-shot Classification across Domainscited by 23
  35. 2022Few-shot Learning with Noisy Labelscited by 23
  36. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  37. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  38. 2023Exploring Efficient Few-shot Adaptation for Vision Transformerscited by 16

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 5; 2025: 2.

13 papers.

Sort:

By area:

  1. 2023DePT: Decoupled Prompt Tuningcited by 58
  2. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  3. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  4. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  5. 2023On the Importance of Spatial Relations for Few-shot Action Recognitioncited by 11
  6. 2024Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselvescited by 10
  7. 2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 9
  8. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 7
  9. 2023ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrievalcited by 6
  10. 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlationcited by 5
  11. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  12. 2023SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentationcited by 1
1 more
  1. 2024Prototype Optimization with Neural ODE for Few-Shot Learningcited by 0