Query Adaptive Few-Shot Object Detection with Heterogeneous Graph
              Convolutional Networks
         Guangxing Han, Yicheng He, Shiyuan Huang, Jiawei Ma, Shih-Fu Chang
                     Columbia University
               {gh2561,yh3330,sh3813,jiawei.m,sc250}@columbia.edu

            Abstract
  Few-shot object detection (FSOD) aims to detect never-
seen objects using few examples. This field sees recent im-
provement owing to the meta-learning techniques by learn-
ing how to match  ...