Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer
It addresses a foundational problem in vision architectures for researchers and practitioners, offering a new paradigm for balancing parameter efficiency and multi-scale representation.
This study tackled the limitations of MLPs in Vision Transformers by introducing Hyb-KAN ViT, which integrates wavelet-based spectral decomposition and spline-optimized activation functions, achieving state-of-the-art performance on ImageNet-1K, COCO, and ADE20K benchmarks.
This study addresses the inherent limitations of Multi-Layer Perceptrons (MLPs) in Vision Transformers (ViTs) by introducing Hybrid Kolmogorov-Arnold Network (KAN)-ViT (Hyb-KAN ViT), a novel framework that integrates wavelet-based spectral decomposition and spline-optimized activation functions, prior work has failed to focus on the prebuilt modularity of the ViT architecture and integration of edge detection capabilities of Wavelet functions. We propose two key modules: Efficient-KAN (Eff-KAN), which replaces MLP layers with spline functions and Wavelet-KAN (Wav-KAN), leveraging orthogonal wavelet transforms for multi-resolution feature extraction. These modules are systematically integrated in ViT encoder layers and classification heads to enhance spatial-frequency modeling while mitigating computational bottlenecks. Experiments on ImageNet-1K (Image Recognition), COCO (Object Detection and Instance Segmentation), and ADE20K (Semantic Segmentation) demonstrate state-of-the-art performance with Hyb-KAN ViT. Ablation studies validate the efficacy of wavelet-driven spectral priors in segmentation and spline-based efficiency in detection tasks. The framework establishes a new paradigm for balancing parameter efficiency and multi-scale representation in vision architectures.