Open AccessPosted Content
When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
Guosheng Hu,Yongxin Yang,Dong Yi,Josef Kittler,William J. Christmas,Stan Z. Li,Timothy M. Hospedales +6 more
Reads0
Chats0
TLDR
In this article, the authors conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make their work easily reproducible, and propose three CNN architectures which are the first reported architectures trained using LFW data.Abstract:Â
Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, unlike most existing CNNs trained on private databases. We propose three CNN architectures which are the first reported architectures trained using LFW data. This paper quantitatively compares the architectures of CNNs and evaluate the effect of different implementation choices. We identify several useful properties of CNN-FRS. For instance, the dimensionality of the learned features can be significantly reduced without adverse effect on face recognition accuracy. In addition, traditional metric learning method exploiting CNN-learned features is evaluated. Experiments show two crucial factors to good CNN-FRS performance are the fusion of multiple CNNs and metric learning. To make our work reproducible, source code and models will be made publicly available.read more
Citations
More filters
Posted Content
CosFace: Large Margin Cosine Loss for Deep Face Recognition
TL;DR: Li et al. as mentioned in this paper reformulated the softmax loss as a cosine loss by normalizing both features and weight vectors to remove radial variations, based on which the cosine margin term is introduced to further maximize the decision margin in the angular space.
Journal ArticleDOI
Predicting flood susceptibility using LSTM neural networks
TL;DR: A local spatial sequential long short-term memory neural network (LSS-LSTM) for flood susceptibility prediction in Shangyou County, China is proposed, which can not only capture both attribution information of flood conditioning factors and local spatial information of flooding data, but also retain the powerful sequential modelling capability to deal with flood spatial relationship.
Proceedings ArticleDOI
Rotation equivariant vector field networks
TL;DR: The Rotation Equivariant Vector Field Networks (RotEqNet), a Convolutional Neural Network architecture encoding rotation equivariance, invariance and covariance, is proposed and a modified convolution operator relying on this representation to obtain deep architectures is developed.
Journal ArticleDOI
Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems
TL;DR: A novel algorithm based on Improved Principal Component Analysis and 1-Dimensional Convolution Neural Network for detection and classification of PQDs is proposed and shows that the proposed method gives significantly higher classification accuracy.
Journal ArticleDOI
Landslide Susceptibility Prediction Modeling Based on Remote Sensing and a Novel Deep Learning Algorithm of a Cascade-Parallel Recurrent Neural Network
TL;DR: A deep-learning-based model using the long short-term memory (LSTM) recurrent neural network and conditional random field in cascade-parallel form was proposed for making LSPs based on remote sensing images and a geographic information system (GIS).
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Posted Content
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Batch Normalization as mentioned in this paper normalizes layer inputs for each training mini-batch to reduce the internal covariate shift in deep neural networks, and achieves state-of-the-art performance on ImageNet.
Proceedings ArticleDOI
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.
Posted Content
Improving neural networks by preventing co-adaptation of feature detectors
TL;DR: The authors randomly omits half of the feature detectors on each training case to prevent complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors.
Proceedings ArticleDOI
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
TL;DR: This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.