Few-Shot Object Detection (FSOD) aims to detect the objects of novel classes using only a few manually annotated samples. With the few novel class samples, learning the inter-class relationships among ...

This work tackles the cross-domain object detection problem which aims to generalize a pre-trained object detector to different domains (driving scenes) without labels. An uncertainty-aware and ...

The coco_classes.txt file contains a list of 80 class names used for object detection in the COCO 2017 dataset. This file can be referenced when training or evaluating models in the Detectron2 and ...