Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912898199060480 |
|---|---|
| author | Hu, Runze Huang, Zihao Li, Xudong Fu, Bohan Zhang, Yan Zhao, Sicheng |
| author_facet | Hu, Runze Huang, Zihao Li, Xudong Fu, Bohan Zhang, Yan Zhao, Sicheng |
| contents | Human visual perception naturally evaluates image quality across multiple scales, a hierarchical process that existing blind image quality assessment (BIQA) algorithms struggle to replicate effectively. This limitation stems from a fundamental misunderstanding: current multi-scale approaches fail to recognize that quality perception varies dramatically between scales -- what appears degraded when viewed closely may look acceptable from a distance. This inconsistency not only creates misleading ``visual illusions'' during feature fusion but also introduces substantial redundant information that dilutes quality-critical features and leads to imprecise assessments. Our CSFIQA framework advances multi-scale BIQA via two key innovations: (1) a selective focus attention mechanism that mimics human visual attention by filtering out redundant cross-scale information that would otherwise mask subtle quality indicators, and (2) a scale contrastive learning strategy that explicitly learns to distinguish quality variations both across and within scales. By incorporating an adaptive noise sample matching mechanism, CSFIQA effectively identifies perceptual quality discrepancies in the same content viewed at different scales. Experiments demonstrate substantial improvements over state-of-the-art methods across seven datasets, achieving up to 8.8% SRCC improvement on challenging real-world distortions, confirming CSFIQA's superior alignment with human quality perception. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09007 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment Hu, Runze Huang, Zihao Li, Xudong Fu, Bohan Zhang, Yan Zhao, Sicheng Computer Vision and Pattern Recognition Human visual perception naturally evaluates image quality across multiple scales, a hierarchical process that existing blind image quality assessment (BIQA) algorithms struggle to replicate effectively. This limitation stems from a fundamental misunderstanding: current multi-scale approaches fail to recognize that quality perception varies dramatically between scales -- what appears degraded when viewed closely may look acceptable from a distance. This inconsistency not only creates misleading ``visual illusions'' during feature fusion but also introduces substantial redundant information that dilutes quality-critical features and leads to imprecise assessments. Our CSFIQA framework advances multi-scale BIQA via two key innovations: (1) a selective focus attention mechanism that mimics human visual attention by filtering out redundant cross-scale information that would otherwise mask subtle quality indicators, and (2) a scale contrastive learning strategy that explicitly learns to distinguish quality variations both across and within scales. By incorporating an adaptive noise sample matching mechanism, CSFIQA effectively identifies perceptual quality discrepancies in the same content viewed at different scales. Experiments demonstrate substantial improvements over state-of-the-art methods across seven datasets, achieving up to 8.8% SRCC improvement on challenging real-world distortions, confirming CSFIQA's superior alignment with human quality perception. |
| title | Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.09007 |