AI Paper Atlas

Research map / Image generation / Image restoration

Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment

Yiwei Lou, Yuanpeng He, Rongchao Zhang, Yongzhi Cao, Hanpin Wang, Yu Huang

AAAI 2026 · Image generation › Image restoration · approach: Priors for restoration networks · 0 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 scene and distortion classification auxiliary tasks (q to q+s+d) with all losses (ablation)DEFNet · Six IQA datasets meanSRCC: 0.922 -> 0.939Improved
add distortion-type task to quality-only model with L^M (ablation)DEFNet · Six IQA datasets meanSRCC: 0.910 -> 0.913Improved
add cross-region loss L^U (q+s+d) (ablation)DEFNet · Six IQA datasets meanSRCC: 0.916 -> 0.925Improved
add cross-grained loss L^F (q+s+d) (ablation)DEFNet · Six IQA datasets meanSRCC: 0.916 -> 0.926Improved
add both L^U and L^F (q+s+d) (ablation)DEFNet · Six IQA datasets meanPLCC: 0.906 -> 0.929Improved
add L^U and L^F to quality-only model (ablation)DEFNet · Six IQA datasets meanSRCC: 0.910 -> 0.922Improved
add L^U to q+s+d model (ablation)DEFNet · Six IQA datasets meanACC_d: 0.851 -> 0.830Hurt
increase lambda_1 from 0.1 to 0.2 (lambda_2=0.1) (ablation)DEFNet · LIVESRCC: 0.978 -> 0.981Improved
increase lambda_1 from 0.1 to 0.4 (lambda_2=0.1) (ablation)DEFNet · LIVE-CPLCC: 0.897 -> 0.821Hurt
increase lambda_2 from 0.1 to 0.3 (lambda_1=0.1) (ablation)DEFNet · LIVE-CPLCC: 0.897 -> 0.867Hurt
use DEFNet evidential fusion instead of LIQEBIQA model · Mean confidence interval widthCI width: 0.286 -> 0.251Improved
use DEFNet instead of UNIQUE on TID2013 zero-shotBIQA model · TID2013 (zero-shot)SRCC: 0.768 -> 0.828Improved

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