DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
Refereed conference paper presented and published in conference proceedings



摘要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 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 [14], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. 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.
著者Ouyang WL, Wang XG, Zeng XY, Qiu S, Luo P, Tian YL, Li HS, Yang S, Wang Z, Loy CC, Tang XO
會議名稱IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
詳細描述DOI: 10.1109/TPAMI.2016.2587642.
頁次2403 - 2412
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence

上次更新時間 2020-07-08 於 02:14