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

Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

2017-03-09
Yu Xiang, Wongun Choi, Yuanqing Lin, Silvio Savarese

Abstract

In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve state-of-the-art performance on both detection and pose estimation on commonly used benchmarks.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1604.04693

PDF

https://arxiv.org/pdf/1604.04693


Similar Posts

Comments