AI Paper Atlas

Research map / Detection and segmentation / CNN features

Region-Adaptive Transform with Segmentation Prior for Image Compression

Yuxi Liu, Wenhan Yang, Huihui Bai, Yunchao Wei, Yao Zhao

ECCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 29 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 Region-Adaptive Transform (RAT) to Zou2022 (ablation)Zou2022 · CLIC Professional ValidBD-rate (%): 0.0 -> -4.35Improved
add Scale Affine Layer (SAL) to Zou2022 (ablation)Zou2022 · CLIC Professional ValidBD-rate (%): 0.0 -> -2.93Improved
combine SAL and RAT (ablation)Zou2022 · CLIC Professional ValidBD-rate (%): 0.0 -> -8.50Improved
use class-agnostic masks as privileged information during training (ablation)SegPIC · COCO-sampleBD-rate (%): +2.10 -> 0 (default)Improved
use real masks instead of 4x4 grid at test time (ablation)SegPIC · COCO-sampleBD-rate (%): 0 -> -0.11No clear effect
finer test grid (8x8) instead of 4x4 (ablation)SegPIC · COCO-sampleBD-rate (%): 0 -> +0.46Hurt
add RAT and SAL to a small baseline without attention or autoregression (ablation)BL-S · Kodak (anchor VTM-17.0)BD-rate (%): +15.5 -> +3.87Improved
add RAT and SAL to Zou2022Zou2022 · Kodak encoding timems: 120 -> 142Hurt

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