Deep face recognition: A survey
TL;DR: A comprehensive review of the recent developments on deep face recognition can be found in this paper, covering broad topics on algorithm designs, databases, protocols, and application scenes, as well as the technical challenges and several promising directions.
About: This article is published in Neurocomputing.The article was published on 2021-03-14 and is currently open access. It has received 353 citations till now. The article focuses on the topics: Deep learning & Feature extraction.
Citations
More filters
05 Jul 2020
TL;DR: An in-depth analysis of existing HAR techniques is provided, concerning the advances proposed to address the HAR’s main challenges, and a comprehensive discussion over the publicly available datasets for the development and evaluation of novel HAR approaches is provided.
Abstract: Human Attribute Recognition (HAR) is a highly active research field in computer vision and pattern recognition domains with various applications such as surveillance or fashion. Several approaches have been proposed to tackle the particular challenges in HAR. However, these approaches have dramatically changed over the last decade, mainly due to the improvements brought by deep learning solutions. To provide insights for future algorithm design and dataset collections, in this survey, (1) we provide an in-depth analysis of existing HAR techniques, concerning the advances proposed to address the HAR’s main challenges; (2) we provide a comprehensive discussion over the publicly available datasets for the development and evaluation of novel HAR approaches; (3) we outline the applications and typical evaluation metrics used in the HAR context.
11 citations
TL;DR: In this paper , a machine learning algorithm called metric learning is used to predict the isomorphism of crystal structures formed by two given chemical compositions with an accuracy of approximately 96.4%.
11 citations
TL;DR: Zhang et al. as discussed by the authors proposed several methods to improve the algorithms for face recognition based on a lightweight CNN, which is further optimized in terms of the network architecture and training pattern on the basis of MobileFaceNet.
Abstract: Face recognition algorithms based on deep learning methods have become increasingly popular. Most of these are based on highly precise but complex convolutional neural networks (CNNs), which require significant computing resources and storage, and are difficult to deploy on mobile devices or embedded terminals. In this paper, we propose several methods to improve the algorithms for face recognition based on a lightweight CNN, which is further optimized in terms of the network architecture and training pattern on the basis of MobileFaceNet. Regarding the network architecture, we introduce the Squeeze-and-Excitation (SE) block and propose three improved structures via a channel attention mechanism—the depthwise SE module, the depthwise separable SE module, and the linear SE module—which are able to learn the correlation of information between channels and assign them different weights. In addition, a novel training method for the face recognition task combined with an additive angular margin loss function is proposed that performs the compression and knowledge transfer of the deep network for face recognition. Finally, we obtained high-precision and lightweight face recognition models with fewer parameters and calculations that are more suitable for applications. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed methods.
11 citations
14 May 2019
TL;DR: This research is the first work to understand the inner works of deep face models, elucidating some particular phenomena in deep face recognition.
Abstract: Deep convolutional neural networks (CNNs) currently have achieved state-of-the-art results on face recognition; yet, the understanding behind the success of the deep face model is still lacking. In particular, it is still unclear the inner workings of deep face model. What effective features does a deep face model learn? What do these features represent and what is the sematic meaning of them? This work explores this problem by analyzing the classic network VGGFace using deep visualization techniques. We first explore features computed by neurons, investigating characters of features like diversity, invariance, discrimination. It’s worth noting that the middle layer is the least robust to transform, which contradicts the conventional view that robustness to transform increases as the network going deeper. The most significant phenomenon we find is that high level features are correspond with complex face attributes which human could not describe using a few words. We present a quantitative analysis on these face attributes perceived by deep CNNs, understanding them and the complex relationships between them. Additionally, we also focus on the significant point, the pose invariance in face recognition. Our research is the first work to understand the inner works of deep face models, elucidating some particular phenomena in deep face recognition.
11 citations
09 Sep 2020
TL;DR: Today’s situation of AI in the context of needs for standardization is looked at, showing that there is a sound basis for starting to work on AI standardization as being undertaken by ISO and other organizations.
Abstract: Many standards development organizations worldwide work on norms for Artificial Intelligence (AI) technologies and AI related processes. At the same time, many governments and companies massively invest in research on AI. It may be asked if AI research has already produced mature technologies and if this field is ready for standardization. This article looks at today’s situation of AI in the context of needs for standardization. The International Organization for Standardization (ISO) runs a standardization project on AI since 2018. We give an up-to-date overview of the status of this work. While a fully comprehensive survey is not the objective, we describe a number of important aspects of the standardization work in AI. In addition, concrete examples for possible items of AI standards are described and discussed. From a scientific point of view, there are many open research questions that make AI standardization appear to be premature. However, our analysis shows that there is a sound basis for starting to work on AI standardization as being undertaken by ISO and other organizations.
11 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
04 Sep 2014TL;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.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
40,257 citations
08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Abstract: We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to ½ everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
38,211 citations