AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DSMix: Distortion-Induced Saliency Map Based Pre-training for No-Reference Image Quality Assessment

Jinsong Shi, Pan Gao, Xiaojiang Peng, Jie Qin

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment

This paper tried a common change: Add a reconstruction / auxiliary loss

add feature reconstruction loss to distillation · CSIQ · SRCC: 0.933 -> 0.941 Improved

What 987 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 DSMix augmentation to pretraining (ablation)Quality encoder (ResNet-50) · CLIVESRCC: 0.773 -> 0.824Improved
add semantic knowledge distillation from ImageNet ResNet-50 (ablation)DSMix pretraining · CLIVESRCC: 0.824 -> 0.873Improved
add cosine distance loss to distillation (ablation)KD · CSIQSRCC: 0.941 -> 0.957 (with L_FR); 0.933 -> 0.950 aloneImproved
add feature reconstruction loss to distillation (ablation)KD · CSIQSRCC: 0.933 -> 0.941Improved
use more KADIS pretraining data (ablation)DSMix pretraining · CSIQSRCC: 0.913 -> 0.948 -> 0.957 (25%, 50%, 100%)Improved
use larger encoder (ablation)Quality encoder · CLIVESRCC: 0.831 -> 0.857 -> 0.873 (ResNet-18/34/50)Improved
replace HyperIQA pretrained weights with DSMixHyperIQA · FLIVESRCC: 0.544 -> 0.631Improved
replace TReS pretrained weights with DSMixTReS · KADIDSRCC: 0.859 -> 0.904Improved
DSMix linear probing vs prior methods on authentic datasetsDSMix · KonIQSRCC: 0.915 vs QPT 0.927No 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