Abstract: Automated object detection in aerial images is crucial in both civil and military applications. Existing computer vision-based object detection methods are not robust enough to precisely ...

Abstract: Object detection is a foundation process in computer vision having widespread applications in autonomous driving, medical diagnostics and security monitoring. Recent advancements and ...

The DINOv3 codebase includes several task-specific heads for a variety of tasks, including classification, depth estimation, object detection, and semantic segmentation. The initial focus of this ...

Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn’t need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed ...