ArcFace: Additive Angular Margin Loss for Deep Face Recognition
15 Jun 2019-pp 4690-4699
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.
Citations
More filters
14 Jun 2020
TL;DR: In this paper, the authors propose a novel unsupervised framework that can synthesize photo-realistic rotated faces using only single-view image collections in the wild, which can serve as a strong self-supervision.
Abstract: Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods. The current generative models heavily rely on datasets with multi-view images of the same person. Thus, their generated results are restricted by the scale and domain of the data source. To overcome these challenges, we propose a novel unsupervised framework that can synthesize photo-realistic rotated faces using only single-view image collections in the wild. Our key insight is that rotating faces in the 3D space back and forth, and re-rendering them to the 2D plane can serve as a strong self-supervision. We leverage the recent advances in 3D face modeling and high-resolution GAN to constitute our building blocks. Since the 3D rotation-and-render on faces can be applied to arbitrary angles without losing details, our approach is extremely suitable for in-the-wild scenarios (i.e. no paired data are available), where existing methods fall short. Extensive experiments demonstrate that our approach has superior synthesis quality as well as identity preservation over the state-of-the-art methods, across a wide range of poses and domains. Furthermore, we validate that our rotate-and-render framework naturally can act as an effective data augmentation engine for boosting modern face recognition systems even on strong baseline models
90 citations
TL;DR: A survey of the state-of-the-art of visual place recognition can be found in this paper, focusing on how it has been shaped by the recent advances in deep learning.
Abstract: In recent years visual place recognition (VPR), i.e., the problem of recognizing the location of images, has received considerable attention from multiple research communities, spanning from computer vision to robotics and even machine learning. This interest is fueled on one hand by the relevance that visual place recognition holds for many applications and on the other hand by the unsolved challenge of making these methods perform reliably in different conditions and environments. This paper presents a survey of the state-of-the-art of research on visual place recognition, focusing on how it has been shaped by the recent advances in deep learning. We start discussing the image representations used in this task and how they have evolved from using hand-crafted to deep-learned features. We further review how metric learning techniques are used to get more discriminative representations, as well as techniques for dealing with occlusions, distractors, and shifts in the visual domain of the images. The survey also provides an overview of the specific solutions that have been proposed for applications in robotics and with aerial imagery. Finally the survey provides a summary of datasets that are used in visual place recognition, highlighting their different characteristics.
89 citations
TL;DR: In this article, the authors review several major subtasks of speaker recognition, including speaker verification, identification, diarization, and robust speaker recognition with a focus on deep learning-based methods.
89 citations
Posted Content•
TL;DR: This work provides a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications.
Abstract: Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years. These models seem a natural fit for handling the ever-increasing scale of biometric recognition problems, from cellphone authentication to airport security systems. Deep learning-based models have increasingly been leveraged to improve the accuracy of different biometric recognition systems in recent years. In this work, we provide a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications. For each biometric, we first introduce the available datasets that are widely used in the literature and their characteristics. We will then talk about several promising deep learning works developed for that biometric, and show their performance on popular public benchmarks. We will also discuss some of the main challenges while using these models for biometric recognition, and possible future directions to which research in this area is headed.
88 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...50 Arcface [111] ResNet-100 MS-Celeb-1M (3....
[...]
...CosFace [110] and ArcFace [111] are two other promis-...
[...]
...CosFace [110] and ArcFace [111] are two other promis- ing face recognition works developed in 2018....
[...]
...Arcface: Additive angular margin loss for deep face recognition....
[...]
...Some of these reported accuracies are taken from [116], where they implemented the Softmax, A-Softmax, CosFace, ArcFace and the AdaptiveFace models with the same 50-layer CNN, for fair comparison....
[...]
TL;DR: Subsets of the FERET and FRGCv2 face databases are used to create a realistic database for training and testing of MAD algorithms, and it is shown that algorithms based on deep face representations can achieve very high detection performance and robustness with respect to various post-processings.
Abstract: The vulnerability of facial recognition systems to face morphing attacks is well known. Many different approaches for morphing attack detection (MAD) have been proposed in the scientific literature. However, the MAD algorithms proposed so far have mostly been trained and tested on datasets whose distributions of image characteristics are either very limited (e.g., only created with a single morphing tool) or rather unrealistic (e.g., no print-scan transformation). As a consequence, these methods easily overfit on certain image types and the results presented cannot be expected to apply to real-world scenarios. For example, the results of the latest NIST FRVT MORPH show that the majority of submitted MAD algorithms lacks robustness and performance when considering unseen and challenging datasets. In this work, subsets of the FERET and FRGCv2 face databases are used to create a realistic database for training and testing of MAD algorithms, containing a large number of ICAO-compliant bona fide facial images, corresponding unconstrained probe images, and morphed images created with four different face morphing tools. Furthermore, multiple post-processings are applied on the reference images, e.g., print-scan and JPEG2000 compression. On this database, previously proposed differential morphing algorithms are evaluated and compared. In addition, the application of deep face representations for differential MAD algorithms is investigated. It is shown that algorithms based on deep face representations can achieve very high detection performance (less than 3% D-EER) and robustness with respect to various post-processings. Finally, the limitations of the developed methods are analyzed.
88 citations
Cites methods from "ArcFace: Additive Angular Margin Lo..."
...The NPP-set of the database is tested against an open-source face recognition system, namely ArcFace [43], and one commercial off-theshelf system, referred to as COTS6....
[...]
...• ArcFace [43], an up-to-date network with a topology optimized for automatic facial recognition • A commercial face recognition SDK from Eyedea7 • A re-implementation8 of the FaceNet algorithm: [45]...
[...]
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
Journal Article•
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Abstract: Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
33,597 citations
Proceedings Article•
06 Jul 2015TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Abstract: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.
30,843 citations
28 Oct 2017
TL;DR: An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.
Abstract: In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models. It builds upon a few projects, most notably Lua Torch, Chainer, and HIPS Autograd [4], and provides a high performance environment with easy access to automatic differentiation of models executed on different devices (CPU and GPU). To make prototyping easier, PyTorch does not follow the symbolic approach used in many other deep learning frameworks, but focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead. Note that this preprint is a draft of certain sections from an upcoming paper covering all PyTorch features.
13,268 citations
Posted Content•
TL;DR: The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.
Abstract: TensorFlow is an interface for expressing machine learning algorithms, and an
implementation for executing such algorithms. A computation expressed using
TensorFlow can be executed with little or no change on a wide variety of
heterogeneous systems, ranging from mobile devices such as phones and tablets
up to large-scale distributed systems of hundreds of machines and thousands of
computational devices such as GPU cards. The system is flexible and can be used
to express a wide variety of algorithms, including training and inference
algorithms for deep neural network models, and it has been used for conducting
research and for deploying machine learning systems into production across more
than a dozen areas of computer science and other fields, including speech
recognition, computer vision, robotics, information retrieval, natural language
processing, geographic information extraction, and computational drug
discovery. This paper describes the TensorFlow interface and an implementation
of that interface that we have built at Google. The TensorFlow API and a
reference implementation were released as an open-source package under the
Apache 2.0 license in November, 2015 and are available at www.tensorflow.org.
10,447 citations