AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Joint Global and Local Hierarchical Priors for Learned Image Compression

Jun-Hyuk Kim, Byeongho Heo, Jong-Seok Lee

CVPR 2022 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 112 citations (OpenAlex)

Check 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
Replace the context and hyperprior entropy model with joint global and local hyperpriorsLearned image compression · Kodak and TecnickRate savings relative to BPGImproved
Use Informer instead of Context+Hyperprior+Global ReferenceLearned image compression · KodakRate savings relative to BPG: 1.74% up to 2.60 %Improved
Use Informer instead of Context+Hyperprior+Global ReferenceEntropy model · 4096×2304GFLOPs: 335.13 -> 329.17Improved
Add the global hyperprior (ablation)Context-only entropy model (Ours w/o Global & Local) · Kodak, λ=0.0067 and λ=0.0483Rate-distortion performanceImproved
Add the local hyperprior alongside the global hyperprior (ablation)Informer · Kodak, λ=0.0067 and λ=0.0483Rate-distortion performanceImproved
Combine Context+Hyperprior with the global hyperprior rather than decompose it into global and local hyperpriors (ablation)Context+Hyperprior+Global · Higher bpp regionRate-distortion performanceHurt
Use the global hyperprior to update the context prior rather than the local hyperprior (ablation)Informer parameter model · Kodak, λ=0.0067 and λ=0.0483Rate-distortion performanceImproved
Use four rather than eight global tokens (ablation)Informer · Lower bpp regionRate-distortion performanceImproved
Use eight rather than four global tokens (ablation)Informer · Higher bpp regionRate-distortion performanceImproved
Introduce global vision with masked self-attention in the context model instead of joint global and local hyperpriors (ablation)Learned image compression · Kodak, λ=0.0067Rate (bpp): 0.2763 -> 0.2842Hurt
Introduce global vision with masked self-attention in the context model instead of joint global and local hyperpriors (ablation)Learned image compression · Kodak, λ=0.0483Rate (bpp): 0.8514 -> 0.8718Hurt

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