papers AI Learner
The Github is limit! Click to go to the new site.

Learning Region Features for Object Detection

2018-03-19
Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai

Abstract

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 fully learnable object detection.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1803.07066

PDF

https://arxiv.org/pdf/1803.07066


Similar Posts

Comments