AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment

Yue Cao, Zhaolin Wan, Dongwei Ren, Zifei Yan, Wangmeng Zuo

CVPR 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 32 citations (OpenAlex)

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 PU learning to SSL to filter outlier unlabeled images (ablation)Proposed FR-IQA network · PIPALSRCC: 0.870 -> 0.874Improved
Add PU learning to SSL to filter outlier unlabeled images (ablation)Proposed FR-IQA network · KADID-10kSRCC: 0.958 -> 0.961Improved
Use unlabeled ESRGAN synthesis without PU outlier filtering (ablation)Proposed FR-IQA network · KADID-10kSRCC: 0.944 -> 0.932Hurt
Add DAB (ablation)Proposed FR-IQA network · PIPALSRCC: 0.824 -> 0.837Improved
Add spatial attention (ablation)Proposed FR-IQA network · PIPALSRCC: 0.857 -> 0.868Improved
Add LocalSW (ablation)Proposed FR-IQA network · PIPALSRCC: 0.849 -> 0.868Improved
Replace global sliced Wasserstein with local distance patches (ablation)Proposed FR-IQA network · PIPALSRCC: 0.755 -> 0.868Improved
Compute spatial attention from reference features rather than distortion features (ablation)Proposed FR-IQA network · PIPAL Val.PLCC: 0.861 -> 0.868Improved
Use spatial attention only instead of channel attention only (ablation)Proposed FR-IQA network · PIPALSRCC: 0.840 -> 0.868Improved
Set τmin to 0.5 rather than 0.4 or 0.6 (ablation)JSPL · PIPALSRCC: 0.870; 0.874; 0.872Improved
Use JSPL rather than supervised learning alone (ablation)Proposed FR-IQA network · LIVESRCC: 0.970 -> 0.980Improved
Use JSPL rather than SSL with ESRGAN unlabeled data (ablation)IQT · PIPAL Val., trained on KADID-10k and ESRGAN SynthesisSRCC: 0.662 -> 0.783Improved

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