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: In RGB-infrared aerial image object detection, fully utilizing the advantages of both RGB and infrared images for effective detection is a key challenge in this field. In response to the ...

Abstract: Oriented object detection in synthetic aperture radar (SAR) images presents significant challenges due to the scarcity of labeled data. In contrast, acquiring labeled optical remote sensing ...