Papers › Test Time Adaptation for Blind Image Quality Assessment

Test Time Adaptation for Blind Image Quality Assessment

27 Jul 2023ICCV 2023 1arXiv:2307.14735archive 2025-07-28

Subhadeep Roy, Shankhanil Mitra, Soma Biswas, Rajiv Soundararajan

While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This motivates the study of test time adaptation (TTA) techniques to improve their performance at inference time. Existing auxiliary tasks and loss functions used for TTA may not be relevant for quality-aware adaptation of the pre-trained model. In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA. In particular, we introduce a group contrastive loss at the batch level and a relative rank loss at the sample level to make the model quality aware and adapt to the target data. Our experiments reveal that even using a small batch of images from the test distribution helps achieve significant improvement in performance by updating the batch normalization statistics of the source model.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shankhanil006/tta-iqa officialmentioned in papermentioned on GitHubjax report
subhadeeproy2000/tta-iqa officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Quality AssessmentNo-Reference Image Quality AssessmentTest-time Adaptation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AWAREBatch Normalization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections