Robust Face Recognition via Multimodal Deep Face Representation

By Changxing Ding, Dacheng Tao. 2015

414 citations recorded by the source corpus.

Face images appearing in multimedia applications, e.g., social networks and digital entertainment, usually exhibit dramatic pose, illumination, and expression variations, resulting in considerable performance degradation for traditional face recognition algorithms. This paper proposes a comprehensive deep learning framework to jointly learn face representation using multimodal information. The proposed deep learning structure is composed of a set of elaborately designed convolutional neural networks (CNNs) and a three-layer stacked auto-encoder (SAE). The set of CNNs extracts complementary facial features from multimodal data. Then, the extracted features are concatenated to form a high-dimensional feature vector, whose dimension is compressed by SAE. All of the CNNs are trained using a subset of 9,000 subjects from the publicly available CASIA-WebFace database, which ensures the reproducibility of this work. Using the proposed single CNN architecture and limited training data, 98.43% verification rate is achieved on the LFW database. Benefitting from the complementary information contained in multimodal data, our small ensemble system achieves higher than 99.0% recognition rate on LFW using publicly available training set.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, neutral): “[2] 1 WebFace 98.”
Fully Learnable Group Convolution for Acceleration of Deep Neural Networks (2019, methodology): “As can be seen, the standard Resnet50 achieves better veriﬁcation rate with giant architecture than [42, 28, 8, 29], inevitably leading to high computational cost.”
MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (2017, methodology): “Autoencoders have been used to tackle a wide range of face-related tasks, including stacked progressive autoencoders for face recognition [24], real-time face alignment [60], face recognition using a supervised autoencoder [13], learning of face representations with a stacked autoencoder [10], or fa”
Deep Multimodal Learning: A Survey on Recent Advances and Trends (2017, methodology): “…deep-learning methods have been applied to various problems involving human activity such as action recognition (an activity can be composed of two or more sequences of shorter actions), gesture recognition [8], gaze-direction estimation [9], face recognition [10], and emotion recognition [11].”
The Multiverse Loss for Robust Transfer Learning (2015, neutral): “0026 25 proprietary,160k Original scratch [41] 0.9773 0.0031 – 1 CASIA [41] Web-Scale Training [33] 0.9800 0.9843 4 proprietary, 500M images MSU TR [38] 0.9745 0.0099 0.9823 0.0068 7 CASIA [41] MMDFR [5] 0.9843 0.0020 0.9902 0.0019 8 proprietary,500k DeepID2 [25] 0.9633 0.9915 0.0013 25 proprietary,”
Disentangled Representation Learning GAN for Pose-Invariant Face Recognition (2017, background): “Second, other work focus on learning discriminative features directly from the non-frontal faces through either one joint model [28,33] or multiple pose-specific models [7,25].”
Deep Face Recognition: A Survey (2018, methodology): “Recently, data augmentation has been widely used in deep FR algorithms [99], [228], [46], [177], [145], [146], [150], [160].”
DehazeNet: An End-to-End System for Single Image Haze Removal (2016, background): “One might be tempted to propose biologically inspired models for image dehazing, by following the success of bio-inspired CNNs for high-level vision tasks such as image classification [19], face recognition [20] and object detection [21].”
Face Recognition Systems: A Survey (2020, background): “For this reason, several recent systems based on 3D data have been developed [3,93,95,128,129].”
Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition (2016, methodology): “We augment the CASIA-WebFace database by horizontal flipping and image jittering [58].”