The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances

Face recognition is one of the most fundamental and long-standing topics in computer vision community. With the recent developments of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in the real-world applications. Given a natural image or video frame as input, an end-to-end deep face recognition system outputs the face feature for recognition. To achieve this, the whole system is generally built with three key elements: face detection, face preprocessing, and face representation. The face detection locates faces in the image or frame. Then, the face preprocessing is proceeded to calibrate the faces to a canonical view and crop them to a normalized pixel size. Finally, in the stage of face representation, the discriminative features are extracted from the preprocessed faces for recognition. All of the three elements are fulfilled by deep convolutional neural networks. In this paper, we present a comprehensive survey about the recent advances of every element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved the capability of them. To start with, we introduce an overview of the end-to-end deep face recognition, which, as mentioned above, includes face detection, face preprocessing, and face representation. Then, we review the deep learning based advances of each element, respectively, covering many aspects such as the up-to-date algorithm designs, evaluation metrics, datasets, performance comparison, existing challenges, and promising directions for future research. We hope this survey could bring helpful thoughts to one for better understanding of the big picture of end-to-end face recognition and deeper exploration in a systematic way.

Learning to Localize Actions from Moments

With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video. Nevertheless, most practical methods still require all training videos to be labeled with temporal annotations (action category and temporal boundary) and develop the models in a fully-supervised manner, despite expensive labeling efforts and inapplicable to new categories. In this paper, we introduce a new design of transfer learning type to learn action localization for a large set of action categories, but only on action moments from the categories of interest and temporal annotations of untrimmed videos from a small set of action classes. Specifically, we present Action Herald Networks (AherNet) that integrate such design into an one-stage action localization framework. Technically, a weight transfer function is uniquely devised to build the transformation between classification of action moments or foreground video segments and action localization in synthetic contextual moments or untrimmed videos. The context of each moment is learnt through the adversarial mechanism to differentiate the generated features from those of background in untrimmed videos. Extensive experiments are conducted on the learning both across the splits of ActivityNet v1.3 and from THUMOS14 to ActivityNet v1.3. Our AherNet demonstrates the superiority even comparing to most fully-supervised action localization methods. More remarkably, we train AherNet to localize actions from 600 categories on the leverage of action moments in Kinetics-600 and temporal annotations from 200 classes in ActivityNet v1.3. Source code and data are available at \url{https://github.com/FuchenUSTC/AherNet}.

CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image

In this paper, we propose a method to recover multi-person 3D mesh from a single image. Existing methods follow a multi-stage detection-based pipeline, where the 3D mesh of each person is regressed from the cropped image patch. They have to suffer from the high complexity of the multi-stage process and the ambiguity of the image-level features. For example, it is hard for them to estimate multi-person 3D mesh from the inseparable crowded cases. Instead, in this paper, we present a novel bottom-up single-shot method, Center-based Human Mesh Recovery network (CenterHMR). The model is trained to simultaneously predict two maps, which represent the location of each human body center and the corresponding parameter vector of 3D human mesh at each center. This explicit center-based representation guarantees the pixel-level feature encoding. Besides, the 3D mesh result of each person is estimated from the features centered at the visible body parts, which improves the robustness under occlusion. CenterHMR surpasses previous methods on multi-person in-the-wild benchmark 3DPW and occlusion dataset 3DOH50K. Besides, CenterHMR has achieved a 2-nd place on ECCV 2020 3DPW Challenge. The code is released on https://github.com/Arthur151/CenterHMR.

Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification

Person re-identification (Re-ID) aims at retrieving an input person image from a set of images captured by multiple cameras. Although recent Re-ID methods have made great success, most of them extract features in terms of the attributes of clothing (e.g., color, texture). However, it is common for people to wear black clothes or be captured by surveillance systems in low light illumination, in which cases the attributes of the clothing are severely missing. We call this problem the Black Re-ID problem. To solve this problem, rather than relying on the clothing information, we propose to exploit head-shoulder features to assist person Re-ID. The head-shoulder adaptive attention network (HAA) is proposed to learn the head-shoulder feature and an innovative ensemble method is designed to enhance the generalization of our model. Given the input person image, the ensemble method would focus on the head-shoulder feature by assigning a larger weight if the individual insides the image is in black clothing. Due to the lack of a suitable benchmark dataset for studying the Black Re-ID problem, we also contribute the first Black-reID dataset, which contains 1274 identities in training set. Extensive evaluations on the Black-reID, Market1501 and DukeMTMC-reID datasets show that our model achieves the best result compared with the state-of-the-art Re-ID methods on both Black and conventional Re-ID problems. Furthermore, our method is also proved to be effective in dealing with person Re-ID in similar clothing. Our code and dataset are avaliable on https://github.com/xbq1994/.

SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning

A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised learning models. In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. We materialize the supervisory signals through determining whether a pair of samples is from one frame or from one video, and whether a triplet of samples is in the correct temporal order. We uniquely regard the signals as the foundation in contrastive learning and derive a particular form named Sequence Contrastive Learning (SeCo). SeCo shows superior results under the linear protocol on action recognition (Kinetics), untrimmed activity recognition (ActivityNet) and object tracking (OTB-100). More remarkably, SeCo demonstrates considerable improvements over recent unsupervised pre-training techniques, and leads the accuracy by 2.96% and 6.47% against fully-supervised ImageNet pre-training in action recognition task on UCF101 and HMDB51, respectively.

Pre-training for Video Captioning Challenge 2020 Summary

The Pre-training for Video Captioning Challenge 2020 Summary: results and challenge participants' technical reports.

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently. Previous methods have shown their efficiency in face parsing, which however overlook the correlation among different face regions. The correlation is a critical clue about the facial appearance, pose, expression etc., and should be taken into account for face parsing. To this end, we propose to model and reason the region-wise relations by learning graph representations, and leverage the edge information between regions for optimized abstraction. Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex. Our model learns and reasons over relations between the regions by propagating information across vertices on the graph. Furthermore, we incorporate the edge information to aggregate the pixel-wise features onto vertices, which emphasizes on the features around edges for fine segmentation along edges. The finally learned graph representation is projected back to pixel grids for parsing. Experiments demonstrate that our model outperforms state-of-the-art methods on the widely used Helen dataset, and also exhibits the superior performance on the large-scale CelebAMask-HQ and LaPa dataset. The code is available at https://github.com/tegusi/EAGRNet.

NPCFace: A Negative-Positive Cooperation Supervision for Training Large-scale Face Recognition

Deep face recognition has made remarkable advances in the last few years, while the training scheme still remains challenging in the large-scale data situation where many hard cases occur. Especially in the range of low false accept rate (FAR), there are various hard cases in both positives ($\textit{i.e.}$ intra-class) and negatives ($\textit{i.e.}$ inter-class). In this paper, we study how to make better use of these hard samples for improving the training. The existing training methods deal with the challenge by adding margins in either the positive logit (such as SphereFace, CosFace, ArcFace) or the negative logit (such as MV-softmax, ArcNegFace, CurricularFace). However, the correlation between hard positive and hard negative is overlooked, as well as the relation between the margin in positive logit and the margin in negative logit. We find such correlation is significant, especially in the large-scale dataset, and one can take advantage from it to boost the training via relating the positive and negative margins for each training sample. To this end, we propose an explicit cooperation between positive and negative margins sample-wisely. Given a batch of hard samples, a novel Negative-Positive Cooperation loss, named NPCFace, is formulated, which emphasizes the training on both the negative and positive hard cases via a cooperative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation. Besides, the negative emphasis is implemented with an improved formulation to achieve stable convergence and flexible parameter setting.We validate the effectiveness of our approach on various benchmarks of large-scale face recognition and outperform the previous methods especially in the low FAR range.

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain. However, most existing methods attempt to perform the alignment from a holistic view, ignoring the underlying class-level data structure in the target domain. To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains. We adopt a fine-grained domain discriminator that not only plays as a domain distinguisher, but also differentiates domains at class level. The traditional binary domain labels are also generalized to domain encodings as the supervision signal to guide the fine-grained feature alignment. An analysis with Class Center Distance (CCD) validates that our fine-grained adversarial strategy achieves better class-level alignment compared to other state-of-the-art methods. Our method is easy to implement and its effectiveness is evaluated on three classical domain adaptation tasks, i.e., GTA5 to Cityscapes, SYNTHIA to Cityscapes and Cityscapes to Cross-City. Large performance gains show that our method outperforms other global feature alignment based and class-wise alignment based counterparts. The code is publicly available at https://github.com/JDAI-CV/FADA.

Semi-Siamese Training for Shallow Face Learning

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. $\textit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.