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
08 Apr 2022
TL;DR: The authors investigated the properties of margin-based cross-entropy losses leading to a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker verification and found that constraining the within-speaker covariance matrix could improve the performance of the PLDA.
Abstract: The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker verification. Popular parametric back-ends include the probabilistic linear discriminant analysis (PLDA) and its variants. This paper investigates the properties of margin-based cross-entropy losses leading to such a shift, and aims to find scoring back-ends best suited for speaker verification. In addition, we revisit the pre-processing techniques which have been widely used in the past and assess their effectiveness on large-margin embeddings. Experiments on the state-of-the-art ECAPA-TDNN networks trained with various large-margin softmax cross-entropy losses show a substantial increment in intra-speaker compactness making the conventional PLDA superfluous. In this regard, we found that constraining the within-speaker covariance matrix could improve the performance of the PLDA. It is demonstrated through a series of experiments on the VoxCeleb-1 and SITW core-core test sets with 40 . 8% equal error rate (EER) reduction and 35 . 1% minimum detection cost (minDCF) reduction. It also outperforms cosine scoring consistently with reductions in EER and minDCF by 10 . 9% and 4 . 9% , respectively.
5 citations
01 Jul 2020
TL;DR: This work addresses the task of automatic misogyny identification and categorization from a representation learning perspective, using both a bidirectional LSTM and BERT optimized with the following metric learning loss functions: contrastive loss, triplet loss, center loss, congenerous cosine loss and additive angular margin loss.
Abstract: The task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions In this work, we address this sentence classification task from a representation learning perspective, using both a bidirectional LSTM and BERT optimized with the following metric learning loss functions: contrastive loss, triplet loss, center loss, congenerous cosine loss and additive angular margin loss We set new state-of-the-art for the task with our fine-tuned BERT, whose sentence embeddings can be compared with a simple cosine distance, and we release all our code as open source for easy reproducibility Moreover, we find that almost every loss function performs equally well in this setting, matching the regular cross entropy loss
5 citations
Posted Content•
TL;DR: Cutting-edge 3D CNNs are proposed, where the intermediate volumes of the network are dissected and propagated over depth (time) dimension for future calculations, substantially reducing the number of computations at online operation.
Abstract: Convolutional Neural Networks with 3D kernels (3D CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames. There have been many successful 3D CNN architectures surpassing the state-of-the-art results successively. However, nearly all of them are designed to operate offline creating several serious handicaps during online operation. Firstly, conventional 3D CNNs are not dynamic since their output features represent the complete input clip instead of the most recent frame in the clip. Secondly, they are not temporal resolution-preserving due to their inherent temporal downsampling. Lastly, 3D CNNs are constrained to be used with fixed temporal input size limiting their flexibility. In order to address these drawbacks, we propose dissected 3D CNNs, where the intermediate volumes of the network are dissected and propagated over depth (time) dimension for future calculations, substantially reducing the number of computations at online operation. For action classification, the dissected version of ResNet models performs 74-90% fewer computations at online operation while achieving $\sim$5% better classification accuracy on the Kinetics-600 dataset than conventional 3D ResNet models. Moreover, the advantages of dissected 3D CNNs are demonstrated by deploying our approach onto several vision tasks, which consistently improved the performance.
5 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...In the domain of video face recognition, typical approaches [29, 41, 8] leverage the features obtained by training on big datasets containing still images followed by simple average pooling of the features without emphasis on the quality of every frame....
[...]
TL;DR: Zhang et al. as discussed by the authors proposed a zero-shot contrastive loss for text-guided image style transfer, which can generate images with the same semantic content as the source image without additional fine-tuning or auxiliary networks.
Abstract: Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature. Existing methods require computationally expensive fine-tuning of diffusion models or additional neural network. To address this, here we propose a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks. By leveraging patch-wise contrastive loss between generated samples and original image embeddings in the pre-trained diffusion model, our method can generate images with the same semantic content as the source image in a zero-shot manner. Our approach outperforms existing methods while preserving content and requiring no additional training, not only for image style transfer but also for image-to-image translation and manipulation. Our experimental results validate the effectiveness of our proposed method.
5 citations
01 Oct 2020
TL;DR: A novel generative model called ResCUNet-GAN is proposed to improve UV map completion and improves the original UV-GAN by stacking two U-Nets and enhancing it with multiple-level residual connections and feature fusion.
Abstract: Face recognition is an active research area in computer vision, which has been widely used in various applications such as security, video surveillance and personal identification. Although recent studies in this field have achieved great successes, they usually require an enormous amount of data for training and yet still have difficulties in in-the-wild dataset due to large variation of pose, illumination, expression. Among these unconstrained conditions, pose variation is thought to be the factor that harms face recognition accuracy the most. In order to deal with pose variation, one can fulfill the incomplete UV map extracted from in-the-wild faces, then attach the completed UV map to a fitted 3D mesh and finally generate different 2D faces of arbitrary poses, which then can be used for training or testing face recognition models. In this paper, we propose a novel generative model called ResCUNet-GAN to improve UV map completion. Particularly, we improve the original UV-GAN by stacking two U-Nets and enhancing it with multiple-level residual connections and feature fusion. The experiments on the popular Multi-PIE dataset shows that our model outperforms the original UV-GAN model.
5 citations
Cites methods from "ArcFace: Additive Angular Margin Lo..."
...We then pass the cropped faces through ArcFace [4] to verify if the synthetic frontal face and the ground truth one belong to the same person or not....
[...]
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