{"ID":2842052,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09948","arxiv_id":"2511.09948","title":"Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment","abstract":"Recent efforts have repurposed the Contrastive Language-Image Pre-training (CLIP) model for No-Reference Image Quality Assessment (NR-IQA) by measuring the cosine similarity between the image embedding and textual prompts such as \"a good photo\" or \"a bad photo.\" However, this semantic similarity overlooks a critical yet underexplored cue: the magnitude of the CLIP image features, which we empirically find to exhibit a strong correlation with perceptual quality. In this work, we introduce a novel adaptive fusion framework that complements cosine similarity with a magnitude-aware quality cue. Specifically, we first extract the absolute CLIP image features and apply a Box-Cox transformation to statistically normalize the feature distribution and mitigate semantic sensitivity. The resulting scalar summary serves as a semantically-normalized auxiliary cue that complements cosine-based prompt matching. To integrate both cues effectively, we further design a confidence-guided fusion scheme that adaptively weighs each term according to its relative strength. Extensive experiments on multiple benchmark IQA datasets demonstrate that our method consistently outperforms standard CLIP-based IQA and state-of-the-art baselines, without any task-specific training.","short_abstract":"Recent efforts have repurposed the Contrastive Language-Image Pre-training (CLIP) model for No-Reference Image Quality Assessment (NR-IQA) by measuring the cosine similarity between the image embedding and textual prompts such as \"a good photo\" or \"a bad photo.\" However, this semantic similarity overlooks a critical ye...","url_abs":"https://arxiv.org/abs/2511.09948","url_pdf":"https://arxiv.org/pdf/2511.09948v3","authors":"[\"Zhicheng Liao\",\"Dongxu Wu\",\"Zhenshan Shi\",\"Sijie Mai\",\"Hanwei Zhu\",\"Lingyu Zhu\",\"Yuncheng Jiang\",\"Baoliang Chen\"]","published":"2025-11-13T04:28:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}