Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection

Yu Xiang, Wongun Choi, Yuanqing Lin, Silvio Savarese

WACV 2017 pp. 924-933

doi:10.1109/WACV.2017.108 /wacv/2017/xiang2017wacv-subcategory/

Abstract

In Convolutional Neural Network (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.

PDF WACV Semantic Scholar

Cite

Text

Xiang et al. "Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017. doi:10.1109/WACV.2017.108

Markdown

[Xiang et al. "Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017.](https://mlanthology.org/wacv/2017/xiang2017wacv-subcategory/) doi:10.1109/WACV.2017.108

BibTeX

@inproceedings{xiang2017wacv-subcategory,
  title     = {{Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection}},
  author    = {Xiang, Yu and Choi, Wongun and Lin, Yuanqing and Savarese, Silvio},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2017},
  pages     = {924-933},
  doi       = {10.1109/WACV.2017.108},
  url       = {https://mlanthology.org/wacv/2017/xiang2017wacv-subcategory/}
}