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
20 Feb 2021
14 citations
TL;DR: A novel two-step framework that consists of the image translation module and the feature learning module to obtain an enhanced cross-modality matching system for heterogeneous datasets achieves a better recognition performance in comparison to the state-of-the-art methods.
Abstract: Reducing the cross-modality gap between two different domains is a challenging problem for heterogeneous face recognition (HFR). The current visual domain face recognition system is not easy to solve the discrepancy of cross-modality when two comparing domains are heterogeneous. Moreover, the amount of HFR dataset is significantly insufficient, making it considerable difficulty in training. This paper proposes a novel two-step framework that consists of the image translation module and the feature learning module to obtain an enhanced cross-modality matching system for heterogeneous datasets. First, the image translation module consists of a Preprocessing Chain (PC) method, CycleGAN, and the Siamese network. It enables to meet the conditions for preserving contents along with changing the styles from the source domain to the target domain. Second, in the feature learning module, the training dataset and its translated images are used together for fine-tuning the pre-trained backbone model in the visual domain. This allows for discriminative and robust feature matching of the probe and gallery test datasets in the visual domain. The experimental results are evaluated with two scenarios, using the CUHK Face Sketch FERET (CUFSF) dataset and the CASIA NIR-VIS 2.0 dataset. The proposed method achieves a better recognition performance in comparison to the state-of-the-art methods.
14 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...The generated backbonemodel in the network was used in the same structure, when fine-tuned with the ArcFace....
[...]
...The hyper-parameters of the ArcFace, s and m, were set to 30 and 0.5, respectively, in Eq....
[...]
...[4] J. Deng, J. Guo, N. Xue, and S. Zafeiriou, ‘‘ArcFace: Additive angular margin loss for deep face recognition,’’ in Proc....
[...]
...LArcFace = − 1 N N∑ i=1 log es(cos(θyi+m)) es(cos(θyi+m)) + ∑n j=1,j6=yi e scosθj , (12) where N and n are the batch size and the class number, respectively. θyi is the target (groud truth) angle. m is the angular margin penalty and s is the feature scale....
[...]
...Deep neural network architectures [1], [2], creating novel loss functions [2]–[4], and large-scale face datasets [5]–[7] are the factors that made it possible to increase performance....
[...]
29 Mar 2022
TL;DR: It is concluded that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions and that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications.
Abstract: Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongoing research efforts are engaging these problems from various angles, in most computer vision related cases these approaches can be generalized to investigations of the effects of distribution shifts in image data. In this context, we propose to study the shifts in the learned weights of trained CNN models. Here we focus on the properties of the distributions of dominantly used 3×3 convolution filter kernels. We collected and publicly provide a dataset with over 1.4 billion filters from hundreds of trained CNNs, using a wide range of datasets, architectures, and vision tasks. In a first use case of the proposed dataset, we can show highly relevant properties of many publicly available pre-trained models for practical applications: I) We analyze distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like visual category of the dataset, task, architecture, or layer depth. Based on these results, we conclude that model pre-training can succeed on arbitrary datasets if they meet size and variance conditions. II) We show that many pre-trained models contain degenerated filters which make them less robust and less suitable for fine-tuning on target applications. Data & Project website: https://github.com/paulgavrikov/cnn-filter-db.
14 citations
TL;DR: Wang et al. as discussed by the authors proposed a resolution-aware knowledge distillation (RKD) framework to narrow the cross-resolution variations by transferring knowledge from HR domain to LR domain.
Abstract: Minimizing the computation complexity is essential for the popularization of deep networks in practical applications. Nowadays, most researches attempt to accelerate deep networks by designing new network structure or compressing the network parameters. Meanwhile, transfer learning techniques such as knowledge distillation are utilized to keep the performance of deep models. In this paper, we focus on accelerating deep models and relieving the computation burden by using low-resolution (LR) images as inputs while maintaining competitive performance, which is rarely researched in the current literature. Deep networks may encounter serious performance degradation when using LR inputs because many details are unavailable from LR images. Besides, the existing approaches may fail to learn discriminative features for LR images because of the dramatic appearance variations between LR and high-resolution (HR) images. To tackle with the above problems, we propose a resolution-aware knowledge distillation (RKD) framework to narrow the cross-resolution variations by transferring knowledge from HR domain to LR domain. The proposed framework consists of a HR teacher network and a LR student network. First, we introduce a discriminator and propose an adversarial learning strategy to shrink the variations between inputs with changing resolution. Then we design a cross-resolution knowledge distillation (CRKD) loss to train discriminative student network by exploiting the knowledge of the teacher network. The CRKD loss is consisted of a resolution-aware distillation loss, a pair-wise constraint, and a maximum mean discrepancy loss. Experimental results on person re-identification, image classification, face recognition, and defect segmentation tasks demonstrate that RKD outperforms traditional knowledge distillation method by achieving better performance with lower computation complexities. Furthermore, CRKD surpasses the state-of-the-art knowledge distillation methods in transferring knowledge across different resolutions under RKD framework, especially when coping with large resolution differences.
14 citations
03 May 2021
TL;DR: In this article, the authors propose a network for face recognition which gives an explicit and quantitative quality score at the same time when a feature vector is extracted, and demonstrate three applications of the explicit face quality, one of which is a progressive feature aggregation scheme in online video face recognition.
Abstract: As the deep learning makes big progresses in still-image face recognition, unconstrained video face recognition is still a challenging task due to low quality face images caused by pose, blur, occlusion, illumination etc. In this paper we propose a network for face recognition which gives an explicit and quantitative quality score at the same time when a feature vector is extracted. To our knowledge this is the first network that implements these two functions in one network online. This network is very simple by adding a quality network branch to the baseline network of face recognition. It does not require training datasets with annotated face quality labels. We evaluate this network on both still-image face datasets and video face datasets and achieve the state-of-the-art performance in many cases. This network enables a lot of applications where an explicit face quality scpre is used. We demonstrate three applications of the explicit face quality, one of which is a progressive feature aggregation scheme in online video face recognition. We design an experiment to prove the benefits of using the face quality in this application. Code will be available at https://github.com/deepcam-cn/facequality.
14 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