4 papers
DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs
Jiachen Zhang, Chengtai Li, Jianfeng Ren +3
Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermedia…
Vision KAN: Towards an Attention-Free Backbone for Vision with Kolmogorov-Arnold Networks
Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo +3
Attention mechanisms have become a key module in modern vision backbones due to their ability to model long-range dependencies. However, their quadratic complexity in sequence leng…
MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classification
Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo +2
Recent advancements in deep learning for image classification predominantly rely on convolutional neural networks (CNNs) or Transformer-based architectures. However, these models f…
Activation Space Selectable Kolmogorov-Arnold Networks
Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo +2
The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. How…