mlsanityData to 14 Oct 2026

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

arXiv 2211.12870 ↗First posted 23 Nov 2022cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activations of the model and align activation statistics of the OOD test data to those of the training data. In contrast to existing methods, which model the distribution of entire channels in the ultimate layer of the feature extractor, we model the distribution of each feature in multiple layers across the network. This results in a more fine-grained supervision and makes ActMAD attain state of the art performance on CIFAR-100C and Imagenet-C. ActMAD is also architecture- and task-agnostic, which lets us go beyond image classification, and score 15.4% improvement over previous approaches when evaluating a KITTI-trained object detector on KITTI-Fog. Our experiments highlight that ActMAD can be applied to online adaptation in realistic scenarios, requiring little data to attain its full performance.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

39 of 50 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  8. 2016Layer Normalizationcited by 5,669
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  10. 2016Wide Residual Networkscited by 3,070
  11. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
27 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,659
  2. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  4. 2018Group Normalizationcited by 1,524
  5. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  7. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  9. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  10. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  11. 2022Continual Test-Time Domain Adaptationcited by 525
  12. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  13. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  14. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 403
  15. 2020First return, then explorecited by 266
  16. 2022Test-Time Training with Masked Autoencoderscited by 212
  17. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  18. 2022Parameter-free Online Test-time Adaptationcited by 189
  19. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  20. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  21. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  22. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  23. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  24. 2018Investigating Human Priors for Playing Video Gamescited by 39
  25. 2022Towards Online Domain Adaptive Object Detectioncited by 36
  26. 2022Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignmentcited by 27
  27. 2022Interactron: Embodied Adaptive Object Detectioncited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 10; 2025: 15; 2026: 9.

41 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  2. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalizationcited by 101
  3. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  4. 2025Test-Time Learning for Large Language Modelscited by 50
  5. 2023LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collectionscited by 43
  6. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  7. 2024PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Imagescited by 24
  8. 2024OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptationcited by 17
  9. 2023Evaluation of Test-Time Adaptation Under Computational Time Constraintscited by 15
  10. 2023What, How, and When Should Object Detectors Update in Continually Changing Test Domains?cited by 15
  11. 2025Test-Time Model Adaptation for Quantized Neural Networkscited by 10
  12. 2025TTRV: Test-Time Reinforcement Learning for Vision Language Modelscited by 10
29 more
  1. 2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
  2. 2025Self-Bootstrapping for Versatile Test-Time Adaptationcited by 7
  3. 2024IT3: Idempotent Test-Time Trainingcited by 6
  4. 2024TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Modelscited by 5
  5. 2025Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Trainingcited by 5
  6. 2025Towards Understanding Extrapolation: a Causal Lenscited by 4
  7. 2024Weakly Supervised Test-Time Domain Adaptation for Object Detectioncited by 3
  8. 2025Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detectioncited by 3
  9. 2025Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptationcited by 3
  10. 2025Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Modelscited by 3
  11. 2026FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptationcited by 3
  12. 2025Structural Alignment Improves Graph Test-Time Adaptationcited by 2
  13. 2025PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptationcited by 2
  14. 2023Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditionscited by 1
  15. 2024Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignmentcited by 1
  16. 2025Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmarkcited by 1
  17. 2025Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarioscited by 1
  18. 2024Mitigating the Bias in the Model for Continual Test-Time Adaptationcited by 0
  19. 2024Open-World Test-Time Training: Self-Training with Contrast Learningcited by 0
  20. 2025Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalizationcited by 0
  21. 2025No Pose Estimation? No Problem: Pose-Agnostic and Instance-Aware Test-Time Adaptation for Monocular Depth Estimationcited by 0
  22. 2026Predictive Spectral Calibration for Source-Free Test-Time Regressioncited by 0
  23. 2026CD-Buffer: Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather Object Detectioncited by 0
  24. 2026DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptationcited by 0
  25. 2026Reliable Neural Collapse Approximation for Open-World Test-Time Adaptationcited by 0
  26. 2026Robust Online Aero-Engine Blade Defect Detection via Dual-Alignment Test-Time Adaptationcited by 0
  27. 2026Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibrationcited by 0
  28. 2026On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMscited by 0
  29. 2026Efficient Test-Time Adaptation For Robot Policiescited by 0