Dsfer-Net：一种使用现代Hopfield网络进行双时相变化检测的深度监督与特征检索网络
Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networks
AI总结：
针对双时相变化检测中深度特征提升性能缺乏解释的问题，提出Dsfer-Net，通过全卷积Siamese网络和深度监督特征检索模块增强语义理解，并在三个公开数据集上验证了其优越性。
摘要：
变化检测是高分辨率遥感图像的重要应用，旨在监测和分析地表随时间的变化。由于高分辨率遥感数据量的快速增加和纹理特征的复杂性，已有若干基于深度学习的定量方法被提出。这些方法通过提取深度特征并结合时空信息，优于传统变化检测方法。然而，对于深度特征如何提升检测性能，仍缺乏合理的解释。在我们的研究中，发现现代Hopfield网络层显著增强了语义理解。在本文中，我们提出了一种用于双时相变化检测的深度监督与特征检索网络（Dsfer-Net）。具体而言，通过全卷积Siamese网络联合提取双时相图像的高代表性深度特征。基于双时相图像的时序地理信息，我们设计了特征检索模块以提取差异特征，并以深度监督的方式利用判别信息。此外，我们观察到深度监督的特征检索模块为所提网络在深层中的语义理解提供了可解释的证据。最后，我们的端到端网络通过聚合来自不同层的检索特征和特征对，建立了一个新颖的框架。在三个公开数据集（LEVIR-CD、WHU-CD和CDD）上进行的实验证实了所提Dsfer-Net优于其他最先进的方法。
英文摘要：
Change detection, an essential application for high-resolution remote sensing images, aims to monitor and analyze changes in the land surface over time. Due to the rapid increase in the quantity of high-resolution remote sensing data and the complexity of texture features, several quantitative deep learning-based methods have been proposed. These methods outperform traditional change detection methods by extracting deep features and combining spatial-temporal information. However, reasonable explanations for how deep features improve detection performance are still lacking. In our investigations, we found that modern Hopfield network layers significantly enhance semantic understanding. In this paper, we propose a Deep Supervision and FEature Retrieval network (Dsfer-Net) for bitemporal change detection. Specifically, the highly representative deep features of bitemporal images are jointly extracted through a fully convolutional Siamese network. Based on the sequential geographical information of the bitemporal images, we designed a feature retrieval module to extract difference features and leverage discriminative information in a deeply supervised manner. Additionally, we observed that the deeply supervised feature retrieval module provides explainable evidence of the semantic understanding of the proposed network in its deep layers. Finally, our end-to-end network establishes a novel framework by aggregating retrieved features and feature pairs from different layers. Experiments conducted on three public datasets (LEVIR-CD, WHU-CD, and CDD) confirm the superiority of the proposed Dsfer-Net over other state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
