Abstract: Large Vision-Language Models (LVLMs) suffer from severe object hallucinations, leading them to frequently generate outputs that do not correspond to the image content, significantly reducing ...
Abstract: Many researchers have investigated DETR-based detectors for remote sensing images due to their promising performance. However, most of these studies focus solely on fine-grained categories, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results