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.

/pdf/arcface-additive-angular-margin-loss-for-deep-face-7vvlem659h.pdf

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Convolutional neural networks (CNNs) have been widely used in computer vision community, significantly improving the state-of-the-art. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new supervision signal, called center loss, for face recognition task. Specifically, the center loss simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers. More importantly, we prove that the proposed center loss function is trainable and easy to optimize in the CNNs. With the joint supervision of softmax loss and center loss, we can train a robust CNNs to obtain the deep features with the two key learning objectives, inter-class dispension and intra-class compactness as much as possible, which are very essential to face recognition. It is encouraging to see that our CNNs (with such joint supervision) achieve the state-of-the-art accuracy on several important face recognition benchmarks, Labeled Faces in the Wild (LFW), YouTube Faces (YTF), and MegaFace Challenge. Especially, our new approach achieves the best results on MegaFace (the largest public domain face benchmark) under the protocol of small training set (contains under 500000 images and under 20000 persons), significantly improving the previous results and setting new state-of-the-art for both face recognition and face verification tasks.

/pdf/a-discriminative-feature-learning-approach-for-deep-face-2zrw7nm451.pdf

A Discriminative Feature Learning Approach for Deep Face Recognition

In this paper, we introduce a new large-scale face dataset named VGGFace2. The dataset contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians). The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimise the label noise. We describe how the dataset was collected, in particular the automated and manual filtering stages to ensure a high accuracy for the images of each identity. To assess face recognition performance using the new dataset, we train ResNet-50 (with and without Squeeze-and-Excitation blocks) Convolutional Neural Networks on VGGFace2, on MS-Celeb-1M, and on their union, and show that training on VGGFace2 leads to improved recognition performance over pose and age. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on the IJB-A and IJB-B face recognition benchmarks, exceeding the previous state-of-the-art by a large margin. The dataset and models are publicly available.

VGGFace2: A Dataset for Recognising Faces across Pose and Age

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge 1 show the superiority of A-Softmax loss in FR tasks.

/pdf/sphereface-deep-hypersphere-embedding-for-face-recognition-bof1bk9snh.pdf

SphereFace: Deep Hypersphere Embedding for Face Recognition

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature discrimination. However, the traditional softmax loss of deep CNNs usually lacks the power of discrimination. To address this problem, recently several loss functions such as center loss, large margin softmax loss, and angular softmax loss have been proposed. All these improved losses share the same idea: maximizing inter-class variance and minimizing intra-class variance. In this paper, we propose a novel loss function, namely large margin cosine loss (LMCL), to realize this idea from a different perspective. More specifically, we reformulate the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space. As a result, minimum intra-class variance and maximum inter-class variance are achieved by virtue of normalization and cosine decision margin maximization. We refer to our model trained with LMCL as CosFace. Extensive experimental evaluations are conducted on the most popular public-domain face recognition datasets such as MegaFace Challenge, Youtube Faces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-art performance on these benchmarks, which confirms the effectiveness of our proposed approach.

/pdf/cosface-large-margin-cosine-loss-for-deep-face-recognition-121ajz0nd8.pdf

CosFace: Large Margin Cosine Loss for Deep Face Recognition

Large face datasets are important for advancing face recognition research, but they are tedious to build, because a lot of work has to go into cleaning the huge amount of raw data. To facilitate this task, we describe an approach to building face datasets that starts with detecting faces in images returned from searches for public figures on the Internet, followed by discarding those not belonging to each queried person. We formulate the problem of identifying the faces to be removed as a quadratic programming problem, which exploits the observations that faces of the same person should look similar, have the same gender, and normally appear at most once per image. Our results show that this method can reliably clean a large dataset, leading to a considerable reduction in the work needed to build it. Finally, we are releasing the FaceScrub dataset that was created using this approach. It consists of 141,130 faces of 695 public figures and can be obtained from http://vintage.winklerbros.net/facescrub.html.

A data-driven approach to cleaning large face datasets

This paper presents the techniques employed in our team's submissions to the 2015 Emotion Recognition in the Wild contest, for the sub-challenge of Static Facial Expression Recognition in the Wild. The objective of this sub-challenge is to classify the emotions expressed by the primary human subject in static images extracted from movies. We follow a transfer learning approach for deep Convolutional Neural Network (CNN) architectures. Starting from a network pre-trained on the generic ImageNet dataset, we perform supervised fine-tuning on the network in a two-stage process, first on datasets relevant to facial expressions, followed by the contest's dataset. Experimental results show that this cascading fine-tuning approach achieves better results, compared to a single stage fine-tuning with the combined datasets. Our best submission exhibited an overall accuracy of 48.5% in the validation set and 55.6% in the test set, which compares favorably to the respective 35.96% and 39.13% of the challenge baseline.

Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning

Birds have been widely used as biological indicators for ecological research. They respond quickly to environmental changes and can be used to infer about other organisms (e.g., insects they feed on). Traditional methods for collecting data about birds involves costly human effort. A promising alternative is acoustic monitoring. There are many advantages to recording audio of birds compared to human surveys, including increased temporal and spatial resolution and extent, applicability in remote sites, reduced observer bias, and potentially lower cost. However, it is an open problem for signal processing and machine learning to reliably identify bird sounds in real-world audio data collected in an acoustic monitoring scenario. Some of the major challenges include multiple simultaneously vocalizing birds, other sources of non-bird sound (e.g., buzzing insects), and background noise like wind, rain, and motor vehicles.

/pdf/the-9th-annual-mlsp-competition-new-methods-for-acoustic-4khrtcl7ds.pdf

The 9th annual MLSP competition: New methods for acoustic classification of multiple simultaneous bird species in a noisy environment

Due to the convenience of taking pictures with various digital cameras and mobile devices, people often end up with multiple shots of the same scene with only slight variations. To enhance photo triaging, which is a very common photowork activity, we propose an effective and easy-to-use brush-and-drag interface that allows the user to interactively explore and compare photos within a broader scene context. First, we brush to mark an area of interest on a photo with our finger(s); our tailored segmentation engine automatically determines corresponding image elements among the photos. Then, we can drag the segmented elements from different photos across the screen to explore them simultaneously, and further perform simple finger gestures to interactively rank photos, select favorites for sharing, or to remove unwanted ones. This novel interaction method was implemented on a consumer-level tablet computer and demonstrated to offer effective interactions in a user study.

Brush-and-drag: a multi-touch interface for photo triaging

The MLSP 2013 Bird Classification Challenge requires participants to predict the set of bird species present in audio clips in a given test set, with the aim of maximizing the micro-AUC score computed from the predictions. This report summarizes the 2nd place solution by team Herbal Candy that achieved a micro-AUC score of 0.95050.

Hong-Wei Ng

Papers

A data-driven approach to cleaning large face datasets

Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning

The 9th annual MLSP competition: New methods for acoustic classification of multiple simultaneous bird species in a noisy environment

Brush-and-drag: a multi-touch interface for photo triaging

The 9th annual MLSP competition: Second place