DEIMv2 is an evolution of the DEIM framework while leveraging the rich features from DINOv3. Our method is designed with various model sizes, from an ultra-light version up to S, M, L, and X, to be ...
Abstract: To address the separation of mineral semantic segmentation and foreign object detection in coal mine conveyor belt detection, and the inability of traditional single-task models to balance ...
Abstract: Salient object detection (SOD) for optical remote sensing images (RSIs) still faces inaccurate localization and sensitivity to edge variations. In this letter, we propose FGDiff, a framework ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results