AI Paper Atlas

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

TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts

Youssef Mansour, Xuyang Zhong, Serdar Caglar, Reinhard Heckel

ECCV 2024 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 10 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
adapt the main head at test time with the pseudo-denoising loss instead of keeping it fixed (ablation)TTT-MIM · Average over tasks (batch adaptation)PSNR: 34.36 -> 36.52Improved
adapt the whole model rather than only group-norm affine parameters (ablation)TTT-MIM · Average over tasks (batch adaptation)PSNR: 33.89 -> 36.52Improved
use pseudo-denoising loss instead of Noise2Self loss for the main head (ablation)TTT-MIM · Average over tasks (batch adaptation)PSNR: 35.58 -> 36.52Improved
adapt a pretrained network at test time instead of zero-shot training from scratch (vs Self2Self)Single-image denoising · Average over tasks (excluding DND)PSNR: 33.14 -> 34.26Improved
adapt a pretrained network with 8 iterations instead of Self2Self training for 150k iterationsSingle-image denoising · Computational costtime per image: 1.2 hours -> less than a secondImproved
apply single-image TTT-MIM to Salt & Pepper and Poisson noise shiftsTTT-MIM · ImageNet Poisson noisePSNR: 32.66 -> 32.91No clear effect
adapt to a batch of images instead of a single imageTTT-MIM · SIDDPSNR: 33.58 -> 39.69Improved
choose the optimal early-stopping iteration per dataset using ground truth instead of fixed 8TTT-MIM · Table 1 settingsPSNR: +0.5 dB averageImproved
TTT-MIM vs zero-shot denoisers on CT and fastMRITTT-MIM · fastMRI and CT (single image)PSNR: fastMRI 29.87 vs 31.99 (Self2Self)Hurt

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