• DOI:10.1109/CVPR.2015.7298854
Corpus ID: 11102127

DeepID-Net: Deformable deep convolutional neural networks for object detection

@article{Ouyang2015DeepIDNetDD,
  title={DeepID-Net: Deformable deep convolutional neural networks for object detection},
  author={Wanli Ouyang and Xiaogang Wang and X. Zeng and Shi Qiu and Ping Luo and Yonglong Tian and Hongsheng Li and S. Yang and Zhe Wang and Chen Change Loy and X. Tang},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={2403-2412}
}

Wanli Ouyang, Xiaogang Wang, +8 authors X. Tang

Published 2015

Computer Science, Medicine

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed