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: This work proposes a pyramid diverse attention (PDA) to learn multi-scale diverse local representations automatically and adaptively in face recognition, developed by integrating the PDA into the hierarchical bilinear pooling (HBP) to fuse information from multiple layers effectively.
Abstract: Deep learning has achieved a great success in face recognition (FR), however, few existing models take hierarchical multi-scale local features into consideration. In this work, we propose a hierarchical pyramid diverse attention (HPDA) network. First, it is observed that local patches would play important roles in FR when the global face appearance changes dramatically. Some recent works apply attention modules to locate local patches automatically without relying on face landmarks. Unfortunately, without considering diversity, some learned attentions tend to have redundant responses around some similar local patches, while neglecting other potential discriminative facial parts. Meanwhile, local patches may appear at different scales due to pose variations or large expression changes. To alleviate these challenges, we propose a pyramid diverse attention (PDA) to learn multi-scale diverse local representations automatically and adaptively. More specifically, a pyramid attention is developed to capture multi-scale features. Meanwhile, a diverse learning is developed to encourage models to focus on different local patches and generate diverse local features. Second, almost all existing models focus on extracting features from the last convolutional layer, lacking of local details or small-scale face parts in lower layers. Instead of simple concatenation or addition, we propose to use a hierarchical bilinear pooling (HBP) to fuse information from multiple layers effectively. Thus, the HPDA is developed by integrating the PDA into the HBP. Experimental results on several datasets show the effectiveness of the HPDA, compared to the state-of-the-art methods.
61 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...Global faces based models usually accept whole faces as inputs [22, 34, 19, 28, 3]....
[...]
...global representations where whole faces are regarded as CNN inputs [22, 34, 19, 3]....
[...]
...To get a high-quality dataset, [3] refined the dataset and made it publicly available....
[...]
14 Jun 2020
TL;DR: An effective automatic label noise cleansing framework for face recognition datasets, FaceGraph, which performs global-to-local discrimination to select useful data in a noisy environment and surpasses state-of-the-art performance on the IJB-C benchmark.
Abstract: In the field of face recognition, large-scale web-collected datasets are essential for learning discriminative representations, but they suffer from noisy identity labels, such as outliers and label flips. It is beneficial to automatically cleanse their label noise for improving recognition accuracy. Unfortunately, existing cleansing methods cannot accurately identify noise in the wild. To solve this problem, we propose an effective automatic label noise cleansing framework for face recognition datasets, FaceGraph. Using two cascaded graph convolutional networks, FaceGraph performs global-to-local discrimination to select useful data in a noisy environment. Extensive experiments show that cleansing widely used datasets, such as CASIA-WebFace, VGGFace2, MegaFace2, and MS-Celeb-1M, using the proposed method can improve the recognition performance of state-of-the-art representation learning methods like Arcface. Further, we cleanse massive self-collected celebrity data, namely MillionCelebs, to provide 18.8M images of 636K identities. Training with the new data, Arcface surpasses state-of-the-art performance by a notable margin to reach 95.62% TPR at 1e-5 FPR on the IJB-C benchmark.
60 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...The effectiveness is assessed in terms of the comparative recognition performance of Arcface [15] trained on different datasets....
[...]
...For instance, the Arcface method trained by this new dataset outperforms stateof-the-art performance on the IJB-C by a notable margin....
[...]
...For the real data validation, we evaluate face recognition performance of ResNet [23] models trained on original and cleansed datasets by the Arcface loss [15]....
[...]
...In Table 4, adopting FaceScrub [37] as probe set and using the wash list provided by DeepInsight [15], the results of two MillionCelebs cleansed versions do not differ a lot, but they all outperform other training datasets by a large margin....
[...]
...Table 3: Cleanse 4 face recognition datasets and train deep models by Arcface [15] to test face verification accuracy (%)....
[...]
01 Oct 2019
TL;DR: This paper introduces a new margin-aware reinforcement learning based loss function, namely fair loss, in which each class will learn an appropriate adaptive margin by Deep Q-learning, and trains an agent to learn a margin adaptive strategy for each class, and makes the additive margins for different classes more reasonable.
Abstract: Recently, large-margin softmax loss methods, such as angular softmax loss (SphereFace), large margin cosine loss (CosFace), and additive angular margin loss (ArcFace), have demonstrated impressive performance on deep face recognition. These methods incorporate a fixed additive margin to all the classes, ignoring the class imbalance problem. However, imbalanced problem widely exists in various real-world face datasets, in which samples from some classes are in a higher number than others. We argue that the number of a class would influence its demand for the additive margin. In this paper, we introduce a new margin-aware reinforcement learning based loss function, namely fair loss, in which each class will learn an appropriate adaptive margin by Deep Q-learning. Specifically, we train an agent to learn a margin adaptive strategy for each class, and make the additive margins for different classes more reasonable. Our method has better performance than present large-margin loss functions on three benchmarks, Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace, which demonstrates that our method could learn better face representation on imbalanced face datasets.
59 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...FairLoss Cos and FairLoss Arc represent the methods with our margin adaptive strategy used in CosFace [36] and ArcFace [5], respectively....
[...]
...The other is ResNet50 [10] with a modified structure, proposed in [5], after the last convolutional layer....
[...]
...We fix ‖xi‖ by L2 normalization and re-scale ‖xi‖ to s, following [20, 36, 5]....
[...]
...[5] directly add an angular margin in the angular space and have a more clear geometric interpretation....
[...]
...Corresponding Author tation, several large-margin loss functions have been proposed to improve the generalization ability of softmax loss, such as SphereFace [20], CosFace [36], and ArcFace [5]....
[...]
14 Jun 2020
TL;DR: A novel Domain Balancing (DB) mechanism to handle the long-tailed domain distribution problem, which refers to the fact that a small number of domains frequently appear while other domains far less existing, is proposed.
Abstract: Long-tailed problem has been an important topic in face recognition task. However, existing methods only concentrate on the long-tailed distribution of classes. Differently, we devote to the long-tailed domain distribution problem, which refers to the fact that a small number of domains frequently appear while other domains far less existing. The key challenge of the problem is that domain labels are too complicated (related to race, age, pose, illumination, etc.) and inaccessible in real applications. In this paper, we propose a novel Domain Balancing (DB) mechanism to handle this problem. Specifically, we first propose a Domain Frequency Indicator (DFI) to judge whether a sample is from head domains or tail domains. Secondly, we formulate a light-weighted Residual Balancing Mapping (RBM) block to balance the domain distribution by adjusting the network according to DFI. Finally, we propose a Domain Balancing Margin (DBM) in the loss function to further optimize the feature space of the tail domains to improve generalization. Extensive analysis and experiments on several face recognition benchmarks demonstrate that the proposed method effectively enhances the generalization capacities and achieves superior performance.
58 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...Specifically, our method achieves 95.54% average accuracy, about 0.4% average improvement over ArcFace....
[...]
...To the compared approaches, we compare the proposed method with the baseline Softmax loss and the recently popular state-of-the-arts, including SphereFace [18], CosFace [32] and ArcFace [4]....
[...]
...Recent years have witnessed remarkable progresses in face recognition, with a variety of approaches proposed in the literatures and applied in real applications [18, 32, 4, 7, 6, 42]....
[...]
...Recently, a variety of margin based softmax losses [18, 32, 4] have achieved the state-of-the-art performances....
[...]
...In particular, the proposed method surpasses the best approach ArcFace by an obvious margin (about 0.82% at Rank-1 identification rate and 0.68% verification rate)....
[...]
20 Jun 2021
TL;DR: Wang et al. as mentioned in this paper proposed an unsupervised FIQA method that incorporates similarity distribution distance for face image quality assessment, which generates quality pseudo-labels by calculating the Wasserstein distance between the intra-class and inter-class similarity distributions.
Abstract: In recent years, Face Image Quality Assessment (FIQA) has become an indispensable part of the face recognition system to guarantee the stability and reliability of recognition performance in an unconstrained scenario. For this purpose, the FIQA method should consider both the intrinsic property and the recognizability of the face image. Most previous works aim to estimate the sample-wise embedding uncertainty or pair-wise similarity as the quality score, which only considers the partial information from the intra-class. However, these methods ignore the valuable in-formation from the inter-class, which is for estimating the recognizability of face image. In this work, we argue that a high-quality face image should be similar to its intra-class samples and dissimilar to its inter-class samples. Thus, we propose a novel unsupervised FIQA method that incorporates Similarity Distribution Distance for Face Image Quality Assessment (SDD-FIQA). Our method generates quality pseudo-labels by calculating the Wasserstein Distance (WD) between the intra-class and inter-class similarity distributions. With these quality pseudo-labels, we are capable of training a regression network for quality prediction. Extensive experiments on benchmark datasets demonstrate that the proposed SDD-FIQA surpasses the state-of-the-arts by an impressive margin. Meanwhile, our method shows good generalization across different recognition systems.
58 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
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