AEKAN: Exploring Superpixel-Based AutoEncoder Kolmogorov-Arnold Network for Unsupervised Multimodal Change Detection
- 11 December 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
Abstract
Multimodal change detection (MCD) has garnered significant interest due to its capacity to address a variety of emergencies in a timely and effective manner. However, discrepancies in sensors and imaging techniques often hinder the direct comparison of heterogeneous remote sensing images (HRSIs), making it difficult to extract change information. To overcome this challenge, we propose a novel superpixel-based AutoEncoder Kolmogorov-Arnold Network (AEKAN) for unsupervised MCD. The primary objective of AEKAN is to excavate the latent commonality features between HRSIs. Notably, commonality features in unchanged regions are generally more pronounced than those in changed regions, which can be leveraged to assess change magnitude. To achieve this, the proposed method utilizes the Kolmogorov-Arnold Network (KAN), renowned for its capability to model data distributions, to extract these commonality features between HRSIs. Concretely, the proposed AEKAN consists of a Siamese KAN encoder and dual KAN decoders. The Siamese encoder aims to map HRSIs and extract latent commonality features, while the dual decoders reconstruct original bi-temporal images from these features. Additionally, we incorporate a hierarchical commonality loss function within the Siamese encoder to train AEKAN. This loss function is designed to intentionally guide the network in capturing commonality features by minimizing the discrepancies in features extracted from HRSIs at each layer of the Siamese encoder. The extracted commonality features are then adopted to quantify the change magnitude between images through mean square error. Extensive experiments on five MCD datasets demonstrate that the proposed AEKAN outperforms existing methods. The source code is available at https://github.com/TongfeiLiu/AEKAN-for-MCD.Keywords
Funding Information
- National Natural Science Foundation of China (62271296, 62201334)
- Scientific Research Program Funded by Shaanxi Provincial Education Department (23JP022, 23JP014)
- Key Research and Development Projects of Shaanxi Province (2024GX-YBXM-121)
- Natural Science Foundation of Shaanxi (2024GX-YBXM-121)
This publication has 53 references indexed in Scilit:
- DMF2Net: Dynamic multi-level feature fusion network for heterogeneous remote sensing image change detectionKnowledge-Based Systems, 2024
- CD-GAN: A robust fusion-based generative adversarial network for unsupervised remote sensing change detection with heterogeneous sensorsInformation Fusion, 2024
- Unsupervised spatial self-similarity difference-based change detection method for multi-source heterogeneous imagesPattern Recognition, 2023
- Unsupervised multimodal change detection based on adaptive optimization of structured graphInternational Journal of Applied Earth Observation and Geoinformation, 2023
- Fourier domain structural relationship analysis for unsupervised multimodal change detectionISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Iterative structure transformation and conditional random field based method for unsupervised multimodal change detectionPattern Recognition, 2022
- Structured graph based image regression for unsupervised multimodal change detectionISPRS Journal of Photogrammetry and Remote Sensing, 2022
- A deep translation (GAN) based change detection network for optical and SAR remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Nonlocal patch similarity based heterogeneous remote sensing change detectionPattern Recognition, 2021
- Coupled dictionary learning for unsupervised change detection between multimodal remote sensing imagesComputer Vision and Image Understanding, 2019