Learning Deep Features via Congenerous Cosine Loss for Person Recognition

Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance. In this paper, we propose a novel method to address this task by training a network to obtain robust and representative features. The intuition is that we directly compare and optimize the cosine distance between two features - enlarging inter-class distinction as well as alleviating inner-class variance. We propose a congenerous cosine loss by minimizing the cosine distance between samples and their cluster centroid in a cooperative way. Such a design reduces the complexity and could be implemented via softmax with normalized inputs. Our method also differs from previous work in person recognition that we do not conduct a second training on the test subset. The identity of a person is determined by measuring the similarity from several body regions in the reference set. Experimental results show that the proposed approach achieves better classification accuracy against previous state-of-the-arts.

[1]  Tiejun Huang,et al.  Deep Relative Distance Learning: Tell the Difference between Similar Vehicles , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Dragomir Anguelov,et al.  Contextual Identity Recognition in Personal Photo Albums , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Yu Liu,et al.  Zoom Out-and-In Network with Recursive Training for Object Proposal , 2017, ArXiv.

[5]  Stan Z. Li,et al.  Deep Metric Learning for Practical Person Re-Identification , 2014, ArXiv.

[6]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[7]  Yao Li,et al.  Sequential Person Recognition in Photo Albums with a Recurrent Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Gang Hua,et al.  A Multi-level Contextual Model for Person Recognition in Photo Albums , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Xiaogang Wang,et al.  Multi-Bias Non-linear Activation in Deep Neural Networks , 2016, ICML.

[11]  Nitish Srivastava.  Unsupervised Learning of Visual Representations using Videos , 2015 .

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Seong Joon Oh,et al.  Person Recognition in Personal Photo Collections , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  J. Macalister.  WHO IS IT , 1914 .

[17]  Xiaogang Wang,et al.  Unsupervised Salience Learning for Person Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[19]  Seong Joon Oh,et al.  Faceless Person Recognition: Privacy Implications in Social Media , 2016, ECCV.

[20]  Rainer Stiefelhagen,et al.  “Knock! Knock! Who is it?” probabilistic person identification in TV-series , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Huchuan Lu,et al.  Dual Deep Network for Visual Tracking , 2016, IEEE Transactions on Image Processing.

[22]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[23]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[24]  Ning Zhang,et al.  Beyond frontal faces: Improving Person Recognition using multiple cues , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Shaogang Gong,et al.  Person Re-Identification by Support Vector Ranking , 2010, BMVC.

[26]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[27]  Varun Ramakrishna,et al.  Convolutional Pose Machines , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Meng Yang,et al.  Large-Margin Softmax Loss for Convolutional Neural Networks , 2016, ICML.

[30]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.