AI Paper Atlas

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

Ground-Truth Free Meta-Learning for Deep Compressive Sampling

Xinran Qin, Yuhui Quan, Tongyao Pang, Hui Ji

CVPR 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Extrapolation and single-sample adaptation · 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
Use external meta-learning rather than training without meta-learning (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 33.97 -> 34.85Improved
Add test-time model adaptation (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 34.40 -> 34.85Improved
Use modified MAML rather than standard MAML (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 34.01 -> 34.85Improved
Use iSURE instead of gSURE with Monte Carlo approximation (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 32.57 -> 34.85Improved
Add null-space consistency loss during adaptation (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 34.65 -> 34.85Improved
Adapt biases only rather than all model weights (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 34.82 -> 34.85No clear effect
Adapt biases instead of feature-map gains (ablation)MetaCS · ADNI, radial masks, noiseless and noisyPSNR (dB): 34.58 -> 34.85Improved
Use ensemble inference with noise-perturbed inputs (ablation)MetaCS · ADNI, radial masksPSNR (dB)No clear effect
Jointly use external learning and test-sample adaptationMetaCS · MRI150, ADNI, and Set11PSNR (dB)Improved
Train one model across noise levels rather than training individuallyMetaCS · Set11, 25%, noise levels 1, 5, and 10PSNR (dB): 29.71 -> 29.64Hurt
Test on a measurement matrix different from the training matrixMetaCS · ADNI, noiseless, Gaussian training mask 1/4PSNR drop: -0.07Hurt

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