Contrastive Local Manifold Learning for No-Reference Image Quality Assessment
This work improves no-reference image quality assessment for applications like image processing and computer vision, but it is incremental as it builds on existing contrastive and manifold learning techniques.
The paper tackled the problem of image quality assessment by addressing the oversight of local manifold structures, resulting in significant performance gains with a PLCC of 0.942 on TID2013 and 0.977 on CSIQ compared to previous methods.
Image Quality Assessment (IQA) methods typically overlook local manifold structures, leading to compromised discriminative capabilities in perceptual quality evaluation. To address this limitation, we present LML-IQA, an innovative no-reference IQA (NR-IQA) approach that leverages a combination of local manifold learning and contrastive learning. Our approach first extracts multiple patches from each image and identifies the most visually salient region. This salient patch serves as a positive sample for contrastive learning, while other patches from the same image are treated as intra-class negatives to preserve local distinctiveness. Patches from different images also act as inter-class negatives to enhance feature separation. Additionally, we introduce a mutual learning strategy to improve the model's ability to recognize and prioritize visually important regions. Comprehensive experiments across eight benchmark datasets demonstrate significant performance gains over state-of-the-art methods, achieving a PLCC of 0.942 on TID2013 (compared to 0.908) and 0.977 on CSIQ (compared to 0.965).