Abstract: Domain-adaptive object detection (DAOD) aims to generalize detectors trained in labeled source domains to unlabeled target domains by mitigating domain bias. Recent studies have confirmed ...
Abstract: Accurately estimating the number of objects across different categories is crucial in remote sensing images for applications ranging from urban planning and environmental monitoring to ...
"STFAR: Test-Time Adaptive Object Detection through Self-Training and Feature Alignment Regularization", accepted by Expert Systems with Applications (ESWA), 2026. The arXiv version is also available ...
Create inspiring presentations from customizable templates on any device, no matter where you are. Presentation software allows you to create visually engaging slideshows with text, images, charts, ...