DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

Wanli Ouyang, Xiaogang Wang, Xingyu Zeng, Shi Qiu, Ping Luo, Yonglong Tian, Hongsheng Li, Shuo Yang, Zhe Wang, Chen-Change Loy, Xiaoou Tang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2403-2412

Abstract


In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection diagram 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 generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN, which is the state-of-the-art, from $31\%$ to $50.3\%$ on the ILSVRC2014 detection dataset. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provide a global view for people to understand the deep learning object detection pipeline.

Related Material


[pdf]
[bibtex]
@InProceedings{Ouyang_2015_CVPR,
author = {Ouyang, Wanli and Wang, Xiaogang and Zeng, Xingyu and Qiu, Shi and Luo, Ping and Tian, Yonglong and Li, Hongsheng and Yang, Shuo and Wang, Zhe and Loy, Chen-Change and Tang, Xiaoou},
title = {DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}