Dynamic Relevance Learning for Few-Shot Object Detection

1 code implementation • 4 Aug 2021 • Weijie Liu, Chong Wang, Haohe Li, Shenghao Yu, Jiafei Wu

By adjusting the prediction distribution of the base detector using the output of this GCN, the proposed model serves as a hard auxiliary classification task, which guides the detector to improve the class representation implicitly.

Few-Shot Object Detection Meta-Learning +2