Gated Enhanced RPN and Hybrid-View for Few-Shot Object Detection

Few-Shot Object Detection (FSOD) is designed to detect unseen objects using a few examples. Matching between query image and support instance via metric learning has been shown to be an effective FSOD method. In previous work, the quality of proposals generated by the RPN is not yet high due to the lack of a fine-grained matching strategy, and the detector performs feature integration only at the spatial location level is limited. Therefore, in this paper, we propose a new method for few-shot object detection which obtains high-quality proposals by the Gated Enhanced RPN (GRPN). To further improve the detection performance from different views, we propose a Hybrid-View Detector to categorize proposals more comprehensively. We perform extensive experiments on the MS-COCO benchmark and the experimental results demonstrate the effectiveness of the proposed method and outperform the state-of-the-art on most shot cases.