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
Posted Content•
TL;DR: An innovatory separator, namely the Hyperplane-Assisted Softmax separator (HASeparator), is proposed that demonstrates superior discrimination capabilities, as evaluated on popular image classification benchmarks.
Abstract: Efficient feature learning with Convolutional Neural Networks (CNNs) constitutes an increasingly imperative property since several challenging tasks of computer vision tend to require cascade schemes and modalities fusion. Feature learning aims at CNN models capable of extracting embeddings, exhibiting high discrimination among the different classes, as well as intra-class compactness. In this paper, a novel approach is introduced that has separator, which focuses on an effective hyperplane-based segregation of the classes instead of the common class centers separation scheme. Accordingly, an innovatory separator, namely the Hyperplane-Assisted Softmax separator (HASeparator), is proposed that demonstrates superior discrimination capabilities, as evaluated on popular image classification benchmarks.
4 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...aration [7], indicating small distances between feature vectors of the same class and large distances between vectors of different ones....
[...]
...Finally, ArcFace [7] adopted an additive angular margin, succeeding a quite simple feature discrimintation method that outperformed all previous works in the field on several face recognition benchmarks [19], [20]....
[...]
...In such cases, the exploitation of softmax is not capable of creating discriminative features since it is not explicitly designed for this task [7]....
[...]
...Paying attention to the above instances, one can notice that except for the first case (a), which has already been proved computationally intensive, the rest are based on the approximative notion that weights correspond to the classes’ centers [7], [14]....
[...]
...Among many other retrieval-based tasks, face verification has been greatly benefited by this progress [17], [18], establishing an abundance of methods [7], [9], [14], [15]....
[...]
23 May 2022
TL;DR: The proposed statistical pyramid dense TDNN (SPD-TDNN) with the statistical pyramid pooling module which captures the context information is proposed with extensive experiments on the VoxCeleb1&2 datasets demonstrate that the proposed PSD- TDNN outperforms corresponding D-TDNCs, D-tdNN-SS and ECAPA-TDnn which achieve the state-of-the-art performances on the SV task, with similar model complexity.
Abstract: Recently, speaker verification (SV) techniques relay on deep learning frameworks to extract more informative embedding vectors, which greatly improves the accuracy compared with traditional machine learning methods. The well-known x-vector architecture, a time delay neural network (TDNN), is widely adapted for SV tasks. However, most of existing variants rarely combines the global and sub-region context information and suffer from the local receptive field that is engendered by the standard convolutional operation. In this paper, we propose statistical pyramid dense TDNN (SPD-TDNN) with the statistical pyramid pooling module which captures the context information. Specifically, the developed module adaptively exchanges information among contextual regions from different perspectives, which correspond to multiple parallel branches. The statistics collected by the global-region branch are comprised of mean and standard deviation across the time domain to acquire the more global context information. Extensive experiments on the VoxCeleb1&2 datasets demonstrate that the proposed PSD-TDNN outperforms corresponding D-TDNN, D-TDNN-SS and ECAPA-TDNN which achieve the state-of-the-art performances on the SV task, with similar model complexity.
4 citations
TL;DR: Wang et al. as discussed by the authors designed a classification loss function based on Arcface loss to improve the Mask R-CNN, which introduces an angular distance based on SoftMax loss that distinguishes the objects and backgrounds with higher similarity.
Abstract: The detection of rock particle motion information is the basis for revealing particle motion laws and quantitative analysis. Such a task is crucial in guiding engineering construction, preventing geological disasters, and verifying numerical models of particles. We propose a machine vision method based on video instance segmentation (VIS) to address the motion information detection problem in rock particles under a vibration load. First, we designed a classification loss function based on Arcface loss to improve the Mask R-CNN. This loss function introduces an angular distance based on SoftMax loss that distinguishes the objects and backgrounds with higher similarity. Second, this method combines the abovementioned Mask R-CNN and Deep Simple Online and Real-time Tracking (Deep SORT) to perform rock particle detection, segmentation, and tracking. Third, we utilized the equivalent ellipse characterization method for segmented particles, integrating with the proportional calibration algorithm to test the translation and detecting the rotation by calculating the change in the angle of the ellipse’s major axis. The experimental results show that the improved Mask R-CNN obtains an accuracy of 93.36% on a self-created dataset and also has some advantages on public datasets. Combining the improved Mask R-CNN and Deep SORT could fulfill the VIS with a low ID switching rate while successfully detecting movement information. The average detection errors of translation and rotation are 5.10% and 14.49%, respectively. This study provides an intelligent scheme for detecting movement information of rock particles.
4 citations
30 Nov 2020
TL;DR: Wang et al. as mentioned in this paper proposed a Feature Adaptation Network (FAN) to jointly perform face recognition and normalization in surveillance images, which disentangles the features into identity and non-identity components and adapt the distribution of the identity features.
Abstract: This paper studies face recognition (FR) and normalization in surveillance imagery. Surveillance FR is a challenging problem that has great values in law enforcement. Despite recent progress in conventional FR, less effort has been devoted to surveillance FR. To bridge this gap, we propose a Feature Adaptation Network (FAN) to jointly perform surveillance FR and normalization. Our face normalization mainly acts on the aspect of image resolution, closely related to face super-resolution. However, previous face super-resolution methods require paired training data with pixel-to-pixel correspondence, which is typically unavailable between real-world low-resolution and high-resolution faces. FAN can leverage both paired and unpaired data as we disentangle the features into identity and non-identity components and adapt the distribution of the identity features, which breaks the limit of current face super-resolution methods. We further propose a random scale augmentation scheme to learn resolution robust identity features, with advantages over previous fixed scale augmentation. Extensive experiments on LFW, WIDER FACE, QUML-SurvFace and SCface datasets have shown the effectiveness of our method on surveillance FR and normalization.
4 citations
TL;DR: The probability that the sample belongs to noise can be determined based on the cosine distance of normalized angle center and face feature vector in the margin-based loss functions, and a two-step learning method integrated into the loss function is proposed.
4 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