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
TL;DR: This study harnesses several of the strongest adversarial attacks against deep learning-based face recognition systems considering the cross-resolution domain, and finds that the deep representation attacks represents a much dangerous menace to a face recognition system than the ones based on the classification output independently from the used metric.
10 citations
TL;DR: In this article, a pairwise binary quality pseudo-label is generated based on the face similarity score without additional manual annotation, and a lightweight quality network is trained by performing knowledge distillation on the quality prediction branch of the face recognition network.
Abstract: End-to-end face quality assessment based on deep learning can directly predict the overall quantitative score of face quality, thus helping to control the risk of face recognition system. Thanks to the development of automatic quality pseudo-label generation, most recent methods can use large-scale face datasets to learn the quality model. However, existing methods use regression models to fit the pseudo-labels, which lack attention to samples that are easy to be misidentified, and require large models for training. The paper treats the quality assessment as a classification problem, focusing on difficult samples near the classification boundary. Specifically, pairwise binary quality pseudo-label is generated based on the face similarity score without additional manual annotation. An identification quality loss is used to decouple the pairwise network training. In addition, a lightweight quality network is trained by performing knowledge distillation on the quality prediction branch of the face recognition network. Experiments show that the proposed quality network achieves state-of-the-art results with only 0.45 M parameters and 77 M FLOPs.
10 citations
TL;DR: FeatureStyleEncoder as discussed by the authors maps the given image to both a latent code and a feature tensor, simultaneously, which helps to obtain better perceptual quality and a lower reconstruction error.
Abstract: AbstractWe present a new encoder architecture for the inversion of Generative Adversarial Networks (GAN). The task is to reconstruct a real image from the latent space of a pre-trained GAN. Unlike previous encoder-based methods which predict only a latent code from a real image, the proposed encoder maps the given image to both a latent code and a feature tensor, simultaneously. The feature tensor is key for accurate inversion, which helps to obtain better perceptual quality and lower reconstruction error. We conduct extensive experiments for several style-based generators pre-trained on different data domains. Our method is the first feed-forward encoder to include the feature tensor in the inversion, outperforming the state-of-the-art encoder-based methods for GAN inversion. Additionally, experiments on video inversion show that our method yields a more accurate and stable inversion for videos. This offers the possibility to perform real-time editing in videos. Code is available at https://github.com/InterDigitalInc/FeatureStyleEncoder.KeywordsGAN inversionStyleGAN encoderLatent space
10 citations
Proceedings Article•
14 Mar 2022
TL;DR: PromCSE (Prompt-based Contrastive Learning for Sentence Embeddings), which only trains small-scale Soft Prompt (i.e., a set of trainable vectors) while keeping PLMs fixed, is proposed, which shows the effectiveness of the method compared with the current state-of-the-art sentence embedding models.
Abstract: Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous works may acquire poor performance under domain shift settings, thus hindering the application of sentence representations in practice. We attribute this low performance to the over-parameterization of PLMs with millions of parameters. To alleviate it, we propose PromCSE (Prompt-based Contrastive Learning for Sentence Embeddings), which only trains small-scale \emph{Soft Prompt} (i.e., a set of trainable vectors) while keeping PLMs fixed. Secondly, the commonly used NT-Xent loss function of contrastive learning does not fully exploit hard negatives in supervised learning settings. To this end, we propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power, inspired by the connection between the NT-Xent loss and the Energy-based Learning paradigm. Empirical results on seven standard semantic textual similarity (STS) tasks and a domain-shifted STS task both show the effectiveness of our method compared with the current state-of-the-art sentence embedding models. Our code is publicly avaliable at https://github.com/YJiangcm/PromCSE
10 citations
TL;DR: Wang et al. as mentioned in this paper proposed a Domain-guided Noise-optimization-based Inversion (DNI) method to perform facial image manipulation, which works based on an inverse code that includes a novel domain-guided encoder called Image2latent to project the image to StyleGAN2 latent space, which can reconstruct an input image with high-quality and maintain its semantic meaning well.
Abstract: A style-based architecture (StyleGAN2) yields outstanding results in data-driven unconditional generative image modeling. This work proposes a Domain-guided Noise-optimization-based Inversion (DNI) method to perform facial image manipulation. It works based on an inverse code that includes: 1) a novel domain-guided encoder called Image2latent to project the image to StyleGAN2 latent space, which can reconstruct an input image with high-quality and maintain its semantic meaning well; 2) a noise optimization mechanism in which a set of noise vectors are used to capture the high-frequency details such as image edges, further improving image reconstruction quality; and 3) a mask for seamless image fusion and local style migration. We further propose a novel semantic alignment evaluation pipeline. It evaluates the semantic alignment with an inverse code by using different attribute boundaries. Extensive qualitative and quantitative comparisons show that DNI can capture rich semantic information and achieve a satisfactory image reconstruction. It can realize a variety of facial image manipulation tasks and outperform state of the art.
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