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

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 ...

We introduce a novel open-set benchmark for remote sensing, accompanied by a self-built Vision Question Answering (VQA) remote sensing dataset, TerraVQA, providing a platform for researchers to ...

Abstract: Oriented object detection in remote sensing images (RSIs) relies heavily on costly annotated data. To alleviate this challenge, we propose a straightforward yet powerful approach for ...