mlsanityData to 14 Oct 2026

Feature Augmentation based Test-Time Adaptation

arXiv 2410.14178 ↗First posted 18 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA methods further restrict this by filtering input data for reliability, making the effective data size even smaller and limiting adaptation potential. To address this issue, We propose Feature Augmentation based Test-time Adaptation (FATA), a simple method that fully utilizes the limited amount of input data through feature augmentation. FATA employs Normalization Perturbation to augment features and adapts the model using the FATA loss, which makes the outputs of the augmented and original features similar. FATA is model-agnostic and can be seamlessly integrated into existing models without altering the model architecture. We demonstrate the effectiveness of FATA on various models and scenarios on ImageNet-C and Office-Home, validating its superiority in diverse real-world conditions.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

28 of 40 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  11. 2021Domain Generalization with MixStylecited by 566
  12. 2022Continual Test-Time Domain Adaptationcited by 525
16 more
  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  2. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  4. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  5. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  6. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  7. 2022Contrastive Test-Time Adaptationcited by 261
  8. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  9. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  10. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  11. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  12. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  13. 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
  14. 2023Feature Alignment and Uniformity for Test Time Adaptationcited by 42
  15. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  16. 2023Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shiftscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detectioncited by 1
  2. 2025Hierarchical Adaptive networks with Task vectors for Test-Time Adaptationcited by 0
  3. 2025SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptationcited by 0
  4. 2026Dual Strategies for Test-Time Adaptationcited by 0