Abstract: Object detection in event streams has emerged as a cutting-edge research area, demonstrating superior performance in low-light conditions, scenarios with motion blur, and rapid movements.
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: Source-free object detection (SFOD) transfers a source-trained model to a target domain using only unlabeled data. Most SFOD methods adopt a mean-teacher framework, filtering pseudo labels ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results