对比6种视觉模型，发现SigLIP2和激活函数对图像质量评估至关重要。
Revisiting Vision Language Foundations for No-Reference Image Quality Assessment
- 统一轻量MLP头微调，系统评估六种预训练模型性能。
- SigLIP2表现最佳，简单Sigmoid激活优于ReLU/GELU。
- 提出可学习激活选择机制，提升泛化性并刷新多个数据集纪录。
大规模视觉语言预训练在无参考图像质量评估（NR-IQA）中展现出潜力，但现代视觉变换器基础模型的相对优势尚不明确。本文首次系统评估六种主流预训练主干网络——CLIP、SigLIP2、DINOv2、DINOv3、Perception和ResNet——在NR-IQA任务中的表现，所有模型均采用相同的轻量MLP头部进行微调。研究发现两个此前被忽视的关键因素：(1) SigLIP2始终表现优异；(2) 激活函数的选择出人意料地关键，尤其影响模型泛化能力。值得注意的是，简单Sigmoid激活在多个基准测试中优于常用的ReLU和GELU。基于此发现，我们提出一种可学习的激活选择机制，自适应地为每个通道确定非线性形式，无需人工设计激活函数，显著提升性能，在CLIVE、KADID10K和AGIQA3K上达到新的SRCC领先水平。大量消融实验验证了该方法在不同架构与场景下的有效性，建立高效可靠的NR-IQA基线。
原文摘要 · Abstract (English)
Large-scale vision language pre-training has recently shown promise for no-reference image-quality assessment (NR-IQA), yet the relative merits of modern Vision Transformer foundations remain poorly understood. In this work, we present the first systematic evaluation of six prominent pretrained backbones, CLIP, SigLIP2, DINOv2, DINOv3, Perception, and ResNet, for the task of No-Reference Image Quality Assessment (NR-IQA), each finetuned using an identical lightweight MLP head. Our study uncovers two previously overlooked factors: (1) SigLIP2 consistently achieves strong performance; and (2) the choice of activation function plays a surprisingly crucial role, particularly for enhancing the generalization ability of image quality assessment models. Notably, we find that simple sigmoid activations outperform commonly used ReLU and GELU on several benchmarks. Motivated by this finding, we introduce a learnable activation selection mechanism that adaptively determines the nonlinearity for each channel, eliminating the need for manual activation design, and achieving new state-of-the-art SRCC on CLIVE, KADID10K, and AGIQA3K. Extensive ablations confirm the benefits across architectures and regimes, establishing strong, resource-efficient NR-IQA baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。