Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment

--Kolmogorov-Arnold Network (KAN) has attracted growing interest for its strong function approximation capability. In our previous work, KAN and its variants were explored in score regression for blind image quality assessment (BIQA). However, these models encounter challenges when processing high-dimensional features, leading to limited performance gains and increased computational cost. T o address these issues, we propose T aylorKAN that leverages the T aylor expansions as learnable activation functions to enhance local approximation capability. T o improve the computational efficiency, network depth reduction and feature dimensionality compression are integrated into the T aylorKAN-based score regression pipeline. On five databases (BID, CLIVE, KonIQ, SPAQ, and FLIVE) with authentic distortions, extensive experiments demonstrate that T aylorKAN consistently outperforms the other KAN-related models, indicating that the local approximation via T aylor expansions is more effective than global approximation using orthogonal functions. Its generalization capacity is validated through inter-database experiments. LIND Image Quality Assessment (BIQA) is important in a wide range of industrial applications, including image compression, data transmission, and multimedia entertainment [1].