AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Test Time Adaptation for Blind Image Quality Assessment

Subhadeep Roy, Shankhanil Mitra, Soma Biswas, Rajiv Soundararajan

ICCV 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 20 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 TTA-IQA (rank + group contrastive loss) to source modelTReS, MUSIQ, HyperIQA, MetaIQA · PIPAL (large shift)SROCC: 0.3845 -> 0.4278 (TReS)Improved
add TTA-IQA to source model on LIVE-IQATReS · LIVE-IQASROCC: 0.5435 -> 0.6722Improved
use quality-aware rank+GC loss instead of rotation prediction as auxiliary taskTTA-IQA · KonIQ-10k, MUSIQSROCC: 0.6577 -> 0.6693Improved
rotation prediction beats TTA-IQA on HyperIQA for KonIQ-10k and LIVE-IQAHyperIQA · KonIQ-10kSROCC: TTA-IQA 0.5960 vs rotation 0.6033Mixed
add rank loss to GC loss (ablation)TTA-IQA · PIPAL, TReSSROCC: 0.4666 -> 0.4278Hurt
combine rank and GC loss versus either alone (ablation)TTA-IQA · MUSIQ and MetaIQA across datasetsSROCC: MetaIQA KonIQ 0.5414/0.5580 -> 0.5838Improved
GC loss on extremely distorted images versus rank loss (ablation)TTA-IQA · LIVE-IQA DMOS>70SROCCImproved
rank loss versus GC loss on batches of similar-quality images (ablation)TTA-IQA · LIVE-IQA DMOS 28-44SROCCImproved
choose single distortion type with maximal predicted quality gap instead of summing all three (ablation)rank loss · LIVE-IQASROCC: 0.634 -> 0.671Improved
vary GC group fraction p from 0.25 to 0.5 (ablation)GC loss · KonIQ-10kSROCC: 0.6516 -> 0.6467No clear effect
increase number of groups G from 2 to 4 (ablation)GC loss · KonIQ-10kSROCC: 0.6516 -> 0.6509No clear effect
run more than 4 TTA iterations (ablation)TTA-IQA · CID2013SROCCHurt

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