Euclidean output layer for discriminative feature extraction

Recently, visual features extracted by convolutional neural networks (CNNs) have been widely used in computer vision. Most state-of-the-art CNNs adopt a convolutional layer to map the high dimensional features into the number of the output classes. However, it is not good enough for feature similarity comparison. So we propose a new layer, Euclidean output layer, for extracting discriminative features in this paper. Furthermore, we use the joint supervision of the center loss and the softmax loss to construct a discriminative feature learning network. Experiments show that our network has the ability of compacting the distribution of the learned features and achieves better performance for unclose-set identification problems.

[1]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Gustavo Carneiro,et al.  Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimizing Global Loss Functions , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[4]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[5]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.

[6]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Arnold W. M. Smeulders,et al.  UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking , 2016 .

[8]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

[9]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.

[10]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[11]  Rahul Sukthankar,et al.  MatchNet: Unifying feature and metric learning for patch-based matching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Nikos Komodakis,et al.  Learning to compare image patches via convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Gang Wang,et al.  Gated Siamese Convolutional Neural Network Architecture for Human Re-identification , 2016, ECCV.

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

[15]  Wu Liu,et al.  Siamese neural network based gait recognition for human identification , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Ian D. Reid,et al.  Fast Training of Triplet-Based Deep Binary Embedding Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

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

[19]  Zhuowen Tu,et al.  Deeply-Supervised Nets , 2014, AISTATS.

[20]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[21]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).