AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

RankIQA: Learning From Rankings for No-Reference Image Quality Assessment

Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov

ICCV 2017 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 563 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 ranking pre-training on synthetic distortions followed by fine-tuning on TID2013 (ablation)VGG-16 NR-IQA · TID2013 (all distortions, 80/20 split)SROCC: 0.612 -> 0.780Improved
add fine-tuning on TID2013 after ranking pre-training (ablation)RankIQA · TID2013 (all distortions, 80/20 split)SROCC: 0.623 -> 0.780Improved
train on generated rankings only, without any TID2013 data (ablation)VGG-16 · TID2013 (all distortions, 80/20 split)SROCC: 0.612 -> 0.623Improved
use ranking-only network instead of direct fine-tuning on a hard distortion type (#13) (ablation)RankIQA · TID2013 distortion #13SROCC: 0.725 -> 0.431Hurt
use a deeper network (AlexNet instead of Shallow) for ranking training (ablation)RankIQA · LIVE (from scratch, 80/20 reference-image split)SROCC: 0.937 -> 0.949Improved
use VGG-16 instead of AlexNet for ranking training (ablation)RankIQA · LIVE (from scratch, 80/20 reference-image split)SROCC: 0.949 -> 0.974Improved
initialize ranking network from ImageNet pre-trained weights (ablation)RankIQA VGG-16 · LIVELCC and SROCCImproved
use efficient Siamese backpropagation over all batch pairs instead of random pairs or hard-negative mining (ablation)Siamese ranking network (AlexNet) · JPEG distortion ranking lossconvergence of ranking lossImproved
generate ranked images from Places2 instead of Waterloo (ablation)RankIQA+FT · LIVE (ALL)SROCC: 0.981 -> 0.980No clear effect
generate ranked images from Places2 instead of Waterloo (ablation)RankIQA+FT · LIVE (ALL)LCC: 0.982 -> 0.981No clear effect
use RankIQA+FT instead of the best prior NR-IQA (HOSA)NR-IQA on TID2013 · TID2013 (all distortions, 80/20 split)SROCC: 0.728 -> 0.780Improved

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