Learning Region Features for Object Detection

Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai; The European Conference on Computer Vision (ECCV), 2018, pp. 381-395

While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods. This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable. The proposed method removes most heuristic choices and outperforms its RoI pooling counterparts. It moves further towards emph{fully learnable object detection}.