AI Paper Atlas

Research map / Image generation / Image restoration

Task-Aware Quantization Network for JPEG Image Compression

Jinyoung Choi, Bohyung Han

ECCV 2020 · Image generation › Image restoration · approach: Learned image compression · 77 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
train the quantization table with a classification (cross-entropy) loss instead of standard JPEG tablesJPEG compression · ImageNet val classificationaccuracy at equal bitrateImproved
add a CBAM-like attention module at the end of the quantization CNN (ablation)Task-aware quantization network · ImageNet val classificationaccuracy vs bitrateImproved
interpolate quantization tables from two trained models for bitrate control (ablation)Task-aware quantization network · ImageNet val classificationaccuracy vs bitrateNo clear effect
train with Inception-v3 perceptual loss for captioningTask-aware quantization network · Flickr8k captioningBLEUImproved
train with MSE or MS-SSIM loss instead of standard JPEG tablesTask-aware quantization network · Kodak and ImageNet valPSNR and MS-SSIMImproved
apply task-aware quantization at higher bitrates (above about 0.4 bpp) (ablation)Task-aware quantization network · ImageNet val classificationaccuracy gainNo clear effect

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