AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

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

Muhammad Jehanzeb Mirza, Pol Jané Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof

CVPR 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Align individual spatial activations across multiple layers rather than only the final layer (ablation)ActMAD · KITTI-FogmAP@50: 36.0 -> 47.7Improved
Align individual pixel statistics rather than channel-averaged statistics (ablation)ActMAD · KITTI-FogmAP@50: 38.6 -> 47.7Improved
Use mean and variance alignment instead of central moment difference (ablation)ActMAD · KITTI-FogmAP@50: 41.2 -> 47.7Improved
Use mean and variance alignment instead of central moment difference (ablation)ActMAD · CIFAR-10CTop-1 error (%): 10.5 -> 10.4No clear effect
Update all parameters rather than only affine parameters (ablation)ActMAD · KITTI-FogmAP@50: 45.2 -> 47.7Improved
Update all parameters rather than only affine parameters (ablation)ActMAD · CIFAR-10CTop-1 error (%): 10.6 -> 10.4No clear effect
Reduce the adaptation batch size from 125 to 10 (ablation)ActMAD · ImageNet-C level 5Top-1 error (%): 66.0 -> 72.8Hurt
Adapt with location-aware activation matchingWRN-40-2 · CIFAR-10C level 5Top-1 error (%): 18.3 -> 10.4Improved
Adapt with location-aware activation matchingViT-B/16 · CIFAR-100C level 5Top-1 error (%): 35.1 -> 22.4Improved
Adapt with location-aware activation matchingResNet-18 · ImageNet-C level 5Top-1 error (%): 86.2 -> 66.0Improved
Use ActMAD rather than CoTTA for continuous corruption adaptationWRN-40-2 · CIFAR-10C level 5, continuous adaptationTop-1 error (%): 11.5 -> 11.4No clear effect
Use ActMAD rather than CoTTA for continuous corruption adaptationWRN-40-2 · CIFAR-100C level 5, continuous adaptationTop-1 error (%): 35.7 -> 35.9No clear effect

Later papers that compared with this method

4 later accepted papers report ActMAD as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy