English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Change detection, as an important application for high-resolution remotesensing images, aims to monitor and analyze changes in the land surface overtime. With the rapid growth in the quantity of high-resolution remote sensingdata and the complexity of texture features, a number of quantitative deeplearning-based methods have been proposed. Although these methods outperformtraditional change detection methods by extracting deep features and combiningspatial-temporal information, reasonable explanations about how deep featureswork on improving the detection performance are still lacking. In ourinvestigations, we find that modern Hopfield network layers achieveconsiderable performance in semantic understandings. In this paper, we proposea Deep Supervision and FEature Retrieval network (Dsfer-Net) for bitemporalchange detection. Specifically, the highly representative deep features ofbitemporal images are jointly extracted through a fully convolutional Siamesenetwork. Based on the sequential geo-information of the bitemporal images, wethen design a feature retrieval module to retrieve the difference feature andleverage discriminative information in a deeply supervised manner. We also notethat the deeply supervised feature retrieval module gives explainable proofsabout the semantic understandings of the proposed network in its deep layers.Finally, this end-to-end network achieves a novel framework by aggregating theretrieved features and feature pairs from different layers. Experimentsconducted on three public datasets (LEVIR-CD, WHU-CD, and CDD) confirm thesuperiority of the proposed Dsfer-Net over other state-of-the-art methods. Codewill be available online (https://github.com/ShizhenChang/Dsfer-Net).

Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networks