AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Exposure Normalization and Compensation for Multiple-Exposure Correction

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 65 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 Instance Normalization to align exposure features (ablation)SID with ENC · SICEPSNR: 19.45 -> 20.07Helped
Add normalization distilling loss (ablation)SID with ENC · SICEPSNR: 20.07 -> 20.16Helped
Add exposure distilling loss (ablation)SID with ENC · SICEPSNR: 20.24 -> 20.37Helped
Add parameter regularization when fine-tuning the worst-performing exposure (ablation)DRBN-ENC-4 · SICE underexposurePSNR: 7.92 -> 21.77Helped
Add parameter regularization when fine-tuning the worst-performing exposure (ablation)DRBN-ENC-4 · SICE overexposurePSNR: 19.96 -> 19.57Hurt
Add ENC to DRBNDRBN · ME averagePSNR: 19.52 -> 22.12Helped

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