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 (CD) aims to detect change regions within an image paircaptured at different times, playing a significant role in diverse real-worldapplications. Nevertheless, most of the existing works focus on designingadvanced network architectures to map the feature difference to the finalchange map while ignoring the influence of the quality of the featuredifference. In this paper, we study the CD from a different perspective, i.e.,how to optimize the feature difference to highlight changes and suppressunchanged regions, and propose a novel module denoted as iterativedifference-enhanced transformers (IDET). IDET contains three transformers: twotransformers for extracting the long-range information of the two images andone transformer for enhancing the feature difference. In contrast to theprevious transformers, the third transformer takes the outputs of the first twotransformers to guide the enhancement of the feature difference iteratively. Toachieve more effective refinement, we further propose the multi-scaleIDET-based change detection that uses multi-scale representations of the imagesfor multiple feature difference refinements and proposes a coarse-to-finefusion strategy to combine all refinements. Our final CD method outperformsseven state-of-the-art methods on six large-scale datasets under diverseapplication scenarios, which demonstrates the importance of feature differenceenhancements and the effectiveness of IDET.

IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection