AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Equivariant Imaging: Learning Beyond the Range Space

Dongdong Chen, Julián Tachella, Mike E. Davies

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 109 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
add the equivariance loss (alpha=100) to measurement-consistency training (ablation)EI with residual U-Net · 50-views CT (CT100 test)PSNR (dB): 31.01 -> 36.94Improved
add the equivariance loss (alpha=1) to measurement-consistency training (ablation)EI with residual U-Net · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 5.84 -> 25.14Improved
add the adversarial distribution loss to EIEI · 50-views CT (CT100 test)PSNR (dB): 36.94 -> 36.96No clear effect
add the adversarial distribution loss to EIEI · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 25.14 -> 23.26Hurt
add the equivariance loss to supervised trainingSup (FBPConvNet) · 50-views CT (CT100 test)PSNR (dB): 38.17 -> 38.79Improved
add the equivariance loss to supervised trainingSup · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 26.51 -> 26.75Improved
raise alpha from 100 to 1000 (ablation)EI · 50-views CT (CT100 test)PSNR (dB): 36.94 -> 33.31Hurt
raise alpha from 1 to 10 (ablation)EI · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 25.14 -> 22.96Hurt
lower alpha from 1 to 0.1 (ablation)EI · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 25.14 -> 23.42Hurt
measurement consistency training instead of the plain FBP pseudo-inverseresidual U-Net · 50-views CT (CT100 test)PSNR (dB): 30.24 -> 31.01Improved
measurement consistency training instead of the exact pseudo-inverseresidual U-Net · Inpainting 30% pixels dropped (Urban100 test)PSNR (dB): 5.84 -> 5.84No clear effect
use EI instead of the best DIP architecture on CT reconstructionEI vs DIP-2 · 50-views CT (CT100 test)PSNR (dB): outperforms DIP-2 by 5 dBImproved

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