Kolmogorov-Arnold Network for Remote Sensing Image Semantic Segmentation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；School of Information Science and Engineering, Wuhan University of Science and Technology（武汉科技大学信息科学与工程学院）
Xianping Ma, Ziyao Wang, Yin Hu, Xiaokang Zhang, Man-On Pun
语义分割在遥感应用中发挥着关键作用，其中特征的准确提取与表征对获得高质量结果至关重要。尽管编码器-解码器架构已被广泛使用，但现有方法往往难以充分利用编码器提取的高维特征，也难以在解码过程中高效恢复细节信息。为解决这些问题，我们提出了一种新型语义分割网络，名为DeepKANSeg，它基于新兴的柯尔莫哥洛夫-阿诺德网络（Kolmogorov Arnold Network，KAN）包含两项关键创新。值得注意的是，KAN的优势在于能够将高维复杂函数分解为单变量变换，从而高效灵活地表征数据中的复杂关系。首先，我们引入了一个基于KAN的深度特征精炼模块，名为DeepKAN，用于从高维特征中有效捕捉复杂的空间关系与丰富的语义关系。其次，我们将全局-局部组合解码器中的传统多层感知器（multi-layer perceptron，MLP）层替换为基于KAN的线性层，名为GLKAN。该模块提升了解码器在解码过程中捕捉细粒度细节的能力。为评估所提方法的有效性，我们在两个知名的高分辨率遥感基准数据集上开展了实验，分别是ISPRS Vaihingen和ISPRS Potsdam。结果表明，经KAN增强的分割模型在准确率方面优于现有最优方法，凸显了KAN作为语义分割任务中传统架构有力替代方案的潜力。此外，显式的单变量分解提升了模型的可解释性，这对遥感领域中需要可解释学习的应用尤为有益。
英文摘要：
Semantic segmentation plays a crucial role in remote sensing applications, where the accurate extraction and representation of features are essential for high-quality results. Despite the widespread use of encoder-decoder architectures, existing methods often struggle with fully utilizing the high-dimensional features extracted by the encoder and efficiently recovering detailed information during decoding. To address these problems, we propose a novel semantic segmentation network, namely DeepKANSeg, including two key innovations based on the emerging Kolmogorov Arnold Network (KAN). Notably, the advantage of KAN lies in its ability to decompose high-dimensional complex functions into univariate transformations, enabling efficient and flexible representation of intricate relationships in data. First, we introduce a KAN-based deep feature refinement module, namely DeepKAN to effectively capture complex spatial and rich semantic relationships from high-dimensional features. Second, we replace the traditional multi-layer perceptron (MLP) layers in the global-local combined decoder with KAN-based linear layers, namely GLKAN. This module enhances the decoder's ability to capture fine-grained details during decoding. To evaluate the effectiveness of the proposed method, experiments are conducted on two well-known fine-resolution remote sensing benchmark datasets, namely ISPRS Vaihingen and ISPRS Potsdam. The results demonstrate that the KAN-enhanced segmentation model achieves superior performance in terms of accuracy compared to state-of-the-art methods. They highlight the potential of KANs as a powerful alternative to traditional architectures in semantic segmentation tasks. Moreover, the explicit univariate decomposition provides improved interpretability, which is particularly beneficial for applications requiring explainable learning in remote sensing.
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception
University of Bath（巴斯大学）；Zhejiang University（浙江大学）
LAKAN: Landmark-assisted Adaptive Kolmogorov-Arnold Network for Face Forgery Detection
School of Cyber Science and Technology, University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学）；Anhui Province Key Laboratory of Digital Security（安徽省数字安全重点实验室）
KANO: Kolmogorov-Arnold Neural Operator for Image Super-Resolution
Southeast University（东南大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）；College of Resources and Environment, University of Chinese Academy of Sciences（中国科学院大学资源与环境学院）；Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK（格勒诺布尔阿尔卑斯大学、法国国家科研机构（Inria）、法国国家科学研究中心（CNRS）、格勒诺布尔INP、LJK）
PostHoc FREE Calibrating on Kolmogorov Arnold Networks
Institute for Clarity in Documentation（文献研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康校区）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements
the University of New Orleans（新奥尔良大学）；Naval Research Laboratory（美国海军研究实验室）；US Army Corps of Engineers, Engineer Research and Development Center（美国陆军工程兵团工程研究与发展中心）
QuKAN: A Quantum Circuit Born Machine approach to Quantum Kolmogorov Arnold Networks
Department of Computer Science and Research Initiative QC-AI, RPTU Kaiserslautern-Landau（计算机科学系和QC-AI研究计划，鲁尔-帕绍大学（RPTU）凯斯贝赫-劳恩道分校）；Embedded Intelligence, German Research Center for Artificial Intelligence (DFKI)（嵌入式智能，德国人工智能研究中心（DFKI））；Department of Physics, RPTU Kaiserslautern-Landau（物理系，鲁尔-帕绍大学（RPTU）凯斯贝赫-劳恩道分校）
本研究利用量子电路 Born 机（QCBM）在混合与全量子形式下实现了 KAN 架构，通过预训练残差函数发挥参数化量子电路的表示能力，验证了 QuKAN 架构的可行性、可解释性与性能。
