Qijie Zhao

TL;DR: This paper presents MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules, and conducts a benchmarking study on different methods, components, and their hyper-parameters.

TL;DR: A powerful end-to-end one-stage object detector called M2Det is designed and train by integrating it into the architecture of SSD, and achieve better detection performance than state-of-the-art one- stage detectors.

TL;DR: Wang et al. as mentioned in this paper proposed a multi-level feature pyramid network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales, which achieved state-of-the-art results among one-stage detectors.

TL;DR: This paper proposes a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet), which can be very easily integrated into most state-of-the-art detectors and significantly improve their performances.

TL;DR: A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.