Paper Info
Title
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection.
Abstract
In this paper, we propose multi-stage and deformable deep convolutional neural networks for 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. With the proposed multi-stage training strategy, multiple classifiers are jointly optimized to process samples at different difficulty levels. 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 modeling averaging. The proposed approach ranked \#2 in ILSVRC 2014. It improves the mean averaged precision obtained by RCNN, which is the state-of-the-art of object detection, from $31\%$ to $45\%$. Detailed component-wise analysis is also provided through extensive experimental evaluation.
Year
Venue
Field
2014
CoRR
Object detection,Pattern recognition,Ranking,Computer science,Convolutional neural network,Pooling,Diagram,Artificial intelligence,Deep learning,Machine learning
DocType
Volume
Citations 
Journal
abs/1409.3505
43
PageRank 
References 
Authors
4.41
55
15
Name
Order
Citations
PageRank
Wanli Ouyang12371105.17
Ping Luo22540111.68
Xingyu Zeng332716.08
Shi Qiu425029.03
Yonglong Tian530015.84
Hongsheng Li6151685.29
Shuo Yang7598.76
Zhe Wang819919.26
Yuanjun Xiong933118.71
Chen Qian107925.58
Zhenyao Zhu1156726.75
Ruohui Wang12905.94
Chen Change Loy134484178.56
Xiaogang Wang149647386.70
Xiaoou Tang1515728670.19