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 ...

Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and ...

Abstract: Underwater image detection plays a vital role in various marine applications such as oceanography, underwater robotics, and environmental monitoring. The challenges of underwater imaging, ...

Abstract: Open-world object detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown ...