Abstract: In the field of object detection for remote sensing imagery, the DETR frameworks demonstrate superior accuracy. However, their substantial computational costs and inference latency lag far ...
The dataset is already organized in YOLO format in the steel_dataset/ directory. If you need to reorganize from original format, see utility/reorganize_dataset.py. steel-defect-detection/ ├── ...
Abstract: Small object detection in uncrewed aerial vehicle (UAV) images is one of the critical aspects for its widespread application. However, due to limited feature extraction for small objects and ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results