AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Learning Convolutional Networks for Content-Weighted Image Compression

Mu Li, Wangmeng Zuo, Shuhang Gu, Debin Zhao, David Zhang

CVPR 2018 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 406 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 a learned content-weighted importance map for spatially adaptive bit allocationContent-weighted image compression · KodakSSIMImproved
Use a learned content-weighted importance map for spatially adaptive bit allocationContent-weighted image compression · KodakMSEMixed
Remove the importance map network and importance-map-based rate loss (ablation)Content-weighted image compression · KodakSSIMHurt
Remove the importance map network and importance-map-based rate loss (ablation)Content-weighted image compression · KodakPSNRHurt
Remove the importance map network and importance-map-based rate loss (ablation)Content-weighted image compression · KodakMSEHurt
Add convolutional entropy coding for both binary codes and the importance map (ablation)Content-weighted image compression · Kodakcompression rateImproved
Use convolutional entropy coding for both code components instead of no entropy coding, encoding binary codes alone, or encoding the importance map alone (ablation)Content-weighted image compression · Kodakcompression rateImproved
Replace the convolutional entropy encoder with CABAC using a small context (ablation)Content-weighted image compression · Kodakcompression rateHurt

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