Author
Weihong Deng
Other affiliations: Syracuse University, Tsinghua University, Peking University
Bio: Weihong Deng is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Facial recognition system & Deep learning. The author has an hindex of 33, co-authored 195 publications receiving 6735 citations. Previous affiliations of Weihong Deng include Syracuse University & Tsinghua University.
Papers published on a yearly basis
Papers
More filters
TL;DR: Deep domain adaptation has emerged as a new learning technique to address the lack of massive amounts of labeled data as discussed by the authors, which leverages deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning.
1,211 citations
01 Jul 2017
TL;DR: A new DLP-CNN (Deep Locality-Preserving CNN) method, which aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatters, is proposed.
Abstract: Past research on facial expressions have used relatively limited datasets, which makes it unclear whether current methods can be employed in real world. In this paper, we present a novel database, RAF-DB, which contains about 30000 facial images from thousands of individuals. Each image has been individually labeled about 40 times, then EM algorithm was used to filter out unreliable labels. Crowdsourcing reveals that real-world faces often express compound emotions, or even mixture ones. For all we know, RAF-DB is the first database that contains compound expressions in the wild. Our cross-database study shows that the action units of basic emotions in RAF-DB are much more diverse than, or even deviate from, those of lab-controlled ones. To address this problem, we propose a new DLP-CNN (Deep Locality-Preserving CNN) method, which aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatters. The benchmark experiments on the 7-class basic expressions and 11-class compound expressions, as well as the additional experiments on SFEW and CK+ databases, show that the proposed DLP-CNN outperforms the state-of-the-art handcrafted features and deep learning based methods for the expression recognition in the wild.
746 citations
TL;DR: A comprehensive survey on deep facial expression recognition (FER) can be found in this article, including datasets and algorithms that provide insights into the intrinsic problems of deep FER, including overfitting caused by lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias.
Abstract: With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this paper, we provide a comprehensive survey on deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we describe the standard pipeline of a deep FER system with the related background knowledge and suggestions of applicable implementations for each stage. We then introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. For the state of the art in deep FER, we review existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences, and discuss their advantages and limitations. Competitive performances on widely used benchmarks are also summarized in this section. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems.
712 citations
TL;DR: A comprehensive review on deep facial expression recognition can be found in this article, including datasets and algorithms that provide insights into the problems of overfitting caused by a lack of sufficient training data and expression-unrelated variations.
Abstract: With the transition of facial expression recognition (FER) from laboratory-controlled to in-the-wild conditions and the recent success of deep learning in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this survey, we provide a comprehensive review on deep FER, including datasets and algorithms that provide insights into these problems. First, we introduce available datasets that are widely used and provide data selection and evaluation principles. We then describe the standard pipeline of a deep FER system with related background knowledge and suggestions of applicable implementations. For the state of the art in deep FER, we introduce existing deep networks and training strategies that are designed for FER, and discuss their advantages and limitations. Competitive performances and experimental comparisons on widely used benchmarks are also summarized. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and opportunities in this field as well as future directions for the design of robust deep FER system.
663 citations
TL;DR: Experimental results on the AR and FERET databases show that ESRC has better generalization ability than SRC for undersampled face recognition under variable expressions, illuminations, disguises, and ages.
Abstract: Sparse Representation-Based Classification (SRC) is a face recognition breakthrough in recent years which has successfully addressed the recognition problem with sufficient training images of each gallery subject. In this paper, we extend SRC to applications where there are very few, or even a single, training images per subject. Assuming that the intraclass variations of one subject can be approximated by a sparse linear combination of those of other subjects, Extended Sparse Representation-Based Classifier (ESRC) applies an auxiliary intraclass variant dictionary to represent the possible variation between the training and testing images. The dictionary atoms typically represent intraclass sample differences computed from either the gallery faces themselves or the generic faces that are outside the gallery. Experimental results on the AR and FERET databases show that ESRC has better generalization ability than SRC for undersampled face recognition under variable expressions, illuminations, disguises, and ages. The superior results of ESRC suggest that if the dictionary is properly constructed, SRC algorithms can generalize well to the large-scale face recognition problem, even with a single training image per class.
577 citations
Cited by
More filters
15 Jun 2019
TL;DR: This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.
Abstract: One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that can enhance the discriminative power. Centre loss penalises the distance between deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in the angular space and therefore penalises the angles between deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to its exact correspondence to geodesic distance on a hypersphere. We present arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks which includes a new large-scale image database with trillions of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead. To facilitate future research, the code has been made available.
4,312 citations
Journal Article•
3,940 citations
01 Jan 2021
TL;DR: Transfer learning aims to improve the performance of target learners on target domains by transferring the knowledge contained in different but related source domains as discussed by the authors, in which the dependence on a large number of target-domain data can be reduced for constructing target learners.
Abstract: Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target-domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. Due to the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Unlike previous surveys, this survey article reviews more than 40 representative transfer learning approaches, especially homogeneous transfer learning approaches, from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, over 20 representative transfer learning models are used for experiments. The models are performed on three different data sets, that is, Amazon Reviews, Reuters-21578, and Office-31, and the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.
2,433 citations
26 Apr 2017
TL;DR: In this paper, the angular softmax (A-softmax) loss was proposed to learn angularly discriminative features for deep face recognition under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal interclass distance under a suitably chosen metric space.
Abstract: This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge 1 show the superiority of A-Softmax loss in FR tasks.
2,272 citations
15 Oct 2004
2,118 citations