AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment

Zhihua Wang, Kede Ma

TPAMI 2021 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 35 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
one round of active fine-tuning on gMAD set L1Baseline BIQA · gMAD set L1SRCC: 0.633 -> 0.818Improved
second round of active fine-tuning adding L2Baseline BIQA · gMAD set L3SRCC: 0.818 -> 0.813No clear effect
second round active fine-tuningBaseline BIQA · Waterloo D-testD-test: 0.890 -> 0.881No clear effect
one round of active fine-tuningBaseline BIQA · Waterloo D-testD-test: 0.881 -> 0.890Improved
active fine-tuning round 1Baseline BIQA · KonIQ-10kSRCC: 0.403 -> 0.523Improved
active fine-tuning round 2Baseline BIQA · SPAQSRCC: 0.575 -> 0.633Improved
add gMAD examples versus simple fine-tuning on D2 only (round 2) (ablation)Baseline BIQA · KADID-10k test subsetSRCC: 0.870 -> 0.872No clear effect
add gMAD examples versus simple fine-tuning on D2 only (round 2) (ablation)Baseline BIQA · CSIQ test subsetSRCC: 0.851 -> 0.871Improved
add gMAD examples versus simple fine-tuning on D2 only (round 2) (ablation)Baseline BIQA · TID2013 test subsetSRCC: 0.835 -> 0.828Hurt
fine-tune baseline on D2 after D1 pre-trainingBaseline BIQA · TID2013SRCC: 0.675 -> 0.822Improved
fine-tune baseline on D2 after D1 pre-trainingBaseline BIQA · LIVESRCC: 0.910 -> 0.896Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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