用改进的KAN模型提升图像清晰度评分预测精度。
Exploring Kolmogorov-Arnold networks for realistic image sharpness assessment
- 基于泰勒展开设计新型KAN网络，提升特征拟合能力。
- 在四个数据集上优于支持向量回归，中层特征下效果最佳。
- 首次探索KAN用于图像质量评估，适合图像处理研究者。
分数预测在基于提取特征评估真实图像清晰度中至关重要。近年来，柯尔莫哥洛夫-阿诺德网络（KAN）在数据拟合方面表现突出。本研究提出基于泰勒级数的KAN（TaylorKAN），并在四个真实图像数据库（BID2011、CID2013、CLIVE和KonIQ-10k）上，利用15个中层特征和2048个高层特征进行分数预测。与支持向量回归相比，KAN整体表现具有竞争力或更优，其中使用中层特征时TaylorKAN表现最佳。这是首个将KAN应用于图像质量评估的研究，为相关任务中KAN的选择与优化提供了参考。
原文摘要 · Abstract (English)
Score prediction is crucial in evaluating realistic image sharpness based on collected informative features. Recently, Kolmogorov-Arnold networks (KANs) have been developed and witnessed remarkable success in data fitting. This study introduces the Taylor series-based KAN (TaylorKAN). Then, different KANs are explored in four realistic image databases (BID2011, CID2013, CLIVE, and KonIQ-10k) to predict the scores by using 15 mid-level features and 2048 high-level features. Compared to support vector regression, results show that KANs are generally competitive or superior, and TaylorKAN is the best one when mid-level features are used. This is the first study to investigate KANs on image quality assessment that sheds some light on how to select and further improve KANs in related tasks.
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。