scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

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.

Content maybe subject to copyright    Report

Citations
More filters
Proceedings ArticleDOI
Liuyihan Song1, Pan Pan1, Kang Zhao1, Hao Yang1, Yiming Chen1, Yingya Zhang1, Yinghui Xu1, Rong Jin1 
23 Aug 2020
TL;DR: A novel softmax variation named KNN softmax, which reduces both the GPU memory consumption and computation costs and improves the throughput of training and a fast continuous convergence strategy to reduce total training iterations by adaptively adjusting learning rate and updating model parameters is proposed.
Abstract: In the last decades, extreme classification has become an essential topic for deep learning. It has achieved great success in many areas, especially in computer vision and natural language processing (NLP). However, it is very challenging to train a deep model with millions of classes due to the memory and computation explosion in the last output layer. In this paper, we propose a large-scale training system to address these challenges. First, we build a hybrid parallel training framework to make the training process feasible. Second, we propose a novel softmax variation named KNN softmax, which reduces both the GPU memory consumption and computation costs and improves the throughput of training. Then, to eliminate the communication overhead, we propose a new overlapping pipeline and a gradient sparsification method. Furthermore, we design a fast continuous convergence strategy to reduce total training iterations by adaptively adjusting learning rate and updating model parameters. With the help of all the proposed methods, we gain 3.9× throughput of our training system and reduce almost 60% of training iterations. The experimental results show that using an in-house 256 GPUs cluster, we could train a classifier of 100 million classes on Alibaba Retail Product Dataset in about five days while achieving a comparable accuracy with the naive softmax training process.

17 citations


Cites methods from "ArcFace: Additive Angular Margin Lo..."

  • ...[6] employ a parallel training strategy to support millions-level identities on a single machine efficiently....

    [...]

Proceedings ArticleDOI
TL;DR: In this article, the authors investigated female underrepresentation in the training data is truly the cause of lower accuracy for females on test data, and they trained each on seven subsets with different male/female ratios, totaling forty two trainings, that are tested on three different datasets.
Abstract: Deep learning methods have greatly increased the accuracy of face recognition, but an old problem still persists: accuracy is usually higher for men than women. It is often speculated that lower accuracy for women is caused by under-representation in the training data. This work investigates female under-representation in the training data is truly the cause of lower accuracy for females on test data. Using a state-of-the-art deep CNN, three different loss functions, and two training datasets, we train each on seven subsets with different male/female ratios, totaling forty two trainings, that are tested on three different datasets. Results show that (1) gender balance in the training data does not translate into gender balance in the test accuracy, (2) the “gender gap” in test accuracy is not minimized by a gender-balanced training set, but by a training set with more male images than female images, and (3) training to minimize the accuracy gap does not result in highest female, male or average accuracy.

17 citations

Journal ArticleDOI
TL;DR: In this article , a novel way of visualizing and understanding the vector space before the NNs' output layer is presented, aiming to enlighten the deep feature vectors' properties under classification tasks.
Abstract: One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as feature extractors particularly frequent in an abundance of modern reasoning systems. Their application scope mainly includes complex cascade tasks, like multi-modal recognition and deep Reinforcement Learning (RL). However, NNs induce implicit biases that are difficult to avoid or to deal with and are not met in traditional image descriptors. Moreover, the lack of knowledge for describing the intra-layer properties -and thus their general behavior- restricts the further applicability of the extracted features. With the paper at hand, a novel way of visualizing and understanding the vector space before the NNs' output layer is presented, aiming to enlighten the deep feature vectors' properties under classification tasks. Main attention is paid to the nature of overfitting in the feature space and its adverse effect on further exploitation. We present the findings that can be derived from our model's formulation and we evaluate them on realistic recognition scenarios, proving its prominence by improving the obtained results.

17 citations

Posted Content
TL;DR: In this paper, the authors present a comprehensive analysis of how and why face recognition accuracy differs between men and women, and they show that accuracy is lower for women due to the combination of the impostor distribution for women having a skew toward higher similarity scores, and the genuine distribution for men having a skewed toward lower similarity scores.
Abstract: We present a comprehensive analysis of how and why face recognition accuracy differs between men and women. We show that accuracy is lower for women due to the combination of (1) the impostor distribution for women having a skew toward higher similarity scores, and (2) the genuine distribution for women having a skew toward lower similarity scores. We show that this phenomenon of the impostor and genuine distributions for women shifting closer towards each other is general across datasets of African-American, Caucasian, and Asian faces. We show that the distribution of facial expressions may differ between male/female, but that the accuracy difference persists for image subsets rated confidently as neutral expression. The accuracy difference also persists for image subsets rated as close to zero pitch angle. Even when removing images with forehead partially occluded by hair/hat, the same impostor/genuine accuracy difference persists. We show that the female genuine distribution improves when only female images without facial cosmetics are used, but that the female impostor distribution also degrades at the same time. Lastly, we show that the accuracy difference persists even if a state-of-the-art deep learning method is trained from scratch using training data explicitly balanced between male and female images and subjects.

17 citations

Posted Content
TL;DR: A novel loss function, named Euclidean Margin Softmax (EMS), is proposed that not only minimizes intra-class distances but also maximizes inter- class distances simultaneously simultaneously, enabling us to learn a feature space with high discriminability, leading to highly accurate retrieval.
Abstract: This paper addresses the problem of Sketch-Based Image Retrieval (SBIR), for which bridge the gap between the data representations of sketch images and photo images is considered as the key. Previous works mostly focus on learning a feature space to minimize intra-class distances for both sketches and photos. In contrast, we propose a novel loss function, named Euclidean Margin Softmax (EMS), that not only minimizes intra-class distances but also maximizes inter-class distances simultaneously. It enables us to learn a feature space with high discriminability, leading to highly accurate retrieval. In addition, this loss function is applied to a conditional network architecture, which could incorporate the prior knowledge of whether a sample is a sketch or a photo. We show that the conditional information can be conveniently incorporated to the recently proposed Squeeze and Excitation (SE) module, lead to a conditional SE (CSE) module. Extensive experiments are conducted on two widely used SBIR benchmark datasets. Our approach, although being very simple, achieved new state-of-the-art on both datasets, surpassing existing methods by a large margin.

17 citations

References
More filters
Proceedings ArticleDOI
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
Sergey Ioffe1, Christian Szegedy1
06 Jul 2015
TL;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