Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment
This work improves BIQA for computer vision applications by enhancing alignment with human perception, though it is incremental as it builds on existing multi-scale strategies.
The paper tackled the problem of blind image quality assessment (BIQA) by addressing redundancy and confusion in multi-scale features, proposing a new framework called CSFIQA that achieved leading performance on eight benchmark datasets, with SRCC values such as 0.967 on CSIQ and 0.905 on LIVEC.
Blind image quality assessment (BIQA) serves as a fundamental task in computer vision, yet it often fails to consistently align with human subjective perception. Recent advances show that multi-scale evaluation strategies are promising due to their ability to replicate the hierarchical structure of human vision. However, the effectiveness of these strategies is limited by a lack of understanding of how different image scales influence perceived quality. This paper addresses two primary challenges: the significant redundancy of information across different scales, and the confusion caused by combining features from these scales, which may vary widely in quality. To this end, a new multi-scale BIQA framework is proposed, namely Contrast-Constrained Scale-Focused IQA Framework (CSFIQA). CSFIQA features a selective focus attention mechanism to minimize information redundancy and highlight critical quality-related information. Additionally, CSFIQA includes a scale-level contrastive learning module equipped with a noise sample matching mechanism to identify quality discrepancies across the same image content at different scales. By exploring the intrinsic relationship between image scales and the perceived quality, the proposed CSFIQA achieves leading performance on eight benchmark datasets, e.g., achieving SRCC values of 0.967 (versus 0.947 in CSIQ) and 0.905 (versus 0.876 in LIVEC).