Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment
This is an incremental improvement for researchers in image quality assessment, addressing computational efficiency and performance in high-dimensional score regression.
The authors tackled the challenge of limited performance and high computational cost in blind image quality assessment (BIQA) when using Kolmogorov-Arnold Networks (KAN) with high-dimensional features, by proposing TaylorKAN, which uses Taylor expansions as learnable activation functions to enhance local approximation and integrates depth reduction and feature compression, resulting in consistent outperformance over other KAN-related models on five databases (BID, CLIVE, KonIQ, SPAQ, and FLIVE).
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. To address these issues, we propose TaylorKAN that leverages the Taylor expansions as learnable activation functions to enhance local approximation capability. To improve the computational efficiency, network depth reduction and feature dimensionality compression are integrated into the TaylorKAN-based score regression pipeline. On five databases (BID, CLIVE, KonIQ, SPAQ, and FLIVE) with authentic distortions, extensive experiments demonstrate that TaylorKAN consistently outperforms the other KAN-related models, indicating that the local approximation via Taylor expansions is more effective than global approximation using orthogonal functions. Its generalization capacity is validated through inter-database experiments. The findings highlight the potential of TaylorKAN as an efficient and robust model for high-dimensional score regression.