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
23 Aug 2020
TL;DR: This work proposes a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained fullprecision model and proposes a learnable attentive transfer module to identify the informative channels for alignment.
Abstract: Network quantization is an effective method for network compression. Existing methods train a low-precision network by fine-tuning from a pre-trained model. However, training a low-precision network often requires large-scale labeled data to achieve superior performance. In many real-world scenarios, only limited labeled data are available due to expensive labeling costs or privacy protection. With limited training data, fine-tuning methods may suffer from the overfitting issue and substantial accuracy loss. To alleviate these issues, we introduce transfer learning into network quantization to obtain an accurate low-precision model. Specifically, we propose a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained full-precision model. To this end, we propose a learnable attentive transfer module to identify the informative channels for alignment. In addition, we introduce the Kullback-Leibler (KL) divergence to further help train a low-precision model. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of DTQ.
10 citations
Additional excerpts
...Besides, we adopt LResNet18E-IR [13] as the base model....
[...]
...Besides, we adopt LResNet18E-IR [13] as...
[...]
Journal Article•
TL;DR: Equipped with EqCo, the simplified MoCo (SiMo) achieves comparable accuracy with MoCo v2 on ImageNet (linear evaluation protocol) while only involves 16 negative pairs per query instead of 65536, suggesting that large quantities of negative samples might not be a critical factor in contrastive learning frameworks.
Abstract: In this paper, we propose a method, named EqCo (Equivalent Rules for Contrastive Learning), to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning framework. Inspired by the InfoMax principle, we point that the margin term in contrastive loss needs to be adaptively scaled according to the number of negative pairs in order to keep steady mutual information bound and gradient magnitude. EqCo bridges the performance gap among a wide range of negative sample sizes, so that for the first time, we can use only a few negative pairs (e.g. 16 per query) to perform self-supervised contrastive training on large-scale vision datasets like ImageNet, while with almost no accuracy drop. This is quite a contrast to the widely used large batch training or memory bank mechanism in current practices. Equipped with EqCo, our simplified MoCo (SiMo) achieves comparable accuracy with MoCo v2 on ImageNet (linear evaluation protocol) while only involves 16 negative pairs per query instead of 65536, suggesting that large quantities of negative samples might not be a critical factor in contrastive learning frameworks.
10 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...1 is very common in the field of supervised metric learning, which is usually named margin softmax cross-entropy loss (Deng et al., 2019; Wang et al., 2018; Sun et al., 2020)....
[...]
...Analogously, in the field of supervised metric learning (Deng et al. (2019); Wang et al. (2018); Sun et al. (2020); Wang et al. (2020)), loss in the similar form as Eq....
[...]
TL;DR: In this article , the authors systematically review contemporary approaches for the long-tailed visual recognition task and categorize these methods based on the stage applied as training, fine-tuning, and inference.
10 citations
01 Jan 2022
TL;DR: This work presents a self-supervision strategy called Swap-R&R to overcome the lack of ground-truth in a fully unsupervised manner for joint face rotation and de-occlusion, and shows that this approach can boost the performance of facial recognition and facial expression recognition.
Abstract: Although various face-related tasks have significantly advanced in recent years, occlusion and extreme pose still impede the achievement of higher performance. Existing face rotation or de-occlusion methods only have emphasized the aspect of each problem. In addition, the lack of high-quality paired data remains an obstacle for both methods. In this work, we present a self-supervision strategy called Swap-R&R to overcome the lack of ground-truth in a fully unsupervised manner for joint face rotation and de-occlusion. To generate an input pair for self-supervision, we transfer the occlusion from a face in an image to an estimated 3D face and create a damaged face image, as if rotated from a different pose by rotating twice with the roughly de-occluded face. Furthermore, we propose Complete Face Recovery GAN (CFR-GAN) to restore the collapsed textures and disappeared occlusion areas by leveraging the structural and textural differences between two rendered images. Unlike previous works, which have selected occlusion-free images to obtain ground-truths, our approach does not require human intervention and paired data. We show that our proposed method can generate a de-occluded frontal face image from an occluded profile face image. Moreover, extensive experiments demonstrate that our approach can boost the performance of facial recognition and facial expression recognition. The code is publicly available 1
10 citations
TL;DR: A comparative analysis of recent deep learning based face age progression methods for both adult and child-based face ageing, broken down into three high-level concepts: translation- based, condition-based, and sequence-based FAP.
Abstract: Face Age Progression (FAP) refers to synthesizing face images while simulating ageing effects, thus enabling predicting the future appearance of an individual. The generation of age-progressed face images brings benefits for various applications, ranging from face recognition systems to forensic investigations and digital entertainment. In particular, the recent success achieved with deep generative networks significantly leveraged the quality of age-synthesized face images in terms of visual fidelity, ageing accuracy and identity preservation. However, the high number of contributions in recent years requires systematically structuring new findings and ideas to identify a common taxonomy, accelerate future research and reduce redundancy. Therefore, we present a comparative analysis of recent deep learning based face age progression methods for both adult and child-based face ageing, broken down into three high-level concepts: translation-based, condition-based, and sequence-based FAP. Further, we offer a comprehensive summary of the most common performance evaluation techniques, cross-age datasets, and open challenges to steer future research in the right direction.
10 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