Fang Wen

Yiting Cheng, Fangyun Wei, Jianmin Bao et al.

Domain adaptation for semantic segmentation enables to alleviate the need for large-scale pixel-wise annotations. Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in adaptive segmentation. The most common practice is to perform SSL along with image translation to well align a single domain (the source or target). However, in this single-domain paradigm, unavoidable visual inconsistency raised by image translation may affect subsequent learning. In this paper, based on the observation that domain adaptation frameworks performed in the source and target domain are almost complementary in terms of image translation and SSL, we propose a novel dual path learning (DPL) framework to alleviate visual inconsistency. Concretely, DPL contains two complementary and interactive single-domain adaptation pipelines aligned in source and target domain respectively. The inference of DPL is extremely simple, only one segmentation model in the target domain is employed. Novel technologies such as dual path image translation and dual path adaptive segmentation are proposed to make two paths promote each other in an interactive manner. Experiments on GTA5$\rightarrow$Cityscapes and SYNTHIA$\rightarrow$Cityscapes scenarios demonstrate the superiority of our DPL model over the state-of-the-art methods. The code and models are available at: \url{https://github.com/royee182/DPL}

Shuyang Gu, Dong Chen, Jianmin Bao et al.

We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). We find that this latent-space method is well-suited for text-to-image generation tasks because it not only eliminates the unidirectional bias with existing methods but also allows us to incorporate a mask-and-replace diffusion strategy to avoid the accumulation of errors, which is a serious problem with existing methods. Our experiments show that the VQ-Diffusion produces significantly better text-to-image generation results when compared with conventional autoregressive (AR) models with similar numbers of parameters. Compared with previous GAN-based text-to-image methods, our VQ-Diffusion can handle more complex scenes and improve the synthesized image quality by a large margin. Finally, we show that the image generation computation in our method can be made highly efficient by reparameterization. With traditional AR methods, the text-to-image generation time increases linearly with the output image resolution and hence is quite time consuming even for normal size images. The VQ-Diffusion allows us to achieve a better trade-off between quality and speed. Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.

Xiaoyi Dong, Jianmin Bao, Ting Zhang et al.

This paper explores a better prediction target for BERT pre-training of vision transformers. We observe that current prediction targets disagree with human perception judgment.This contradiction motivates us to learn a perceptual prediction target. We argue that perceptually similar images should stay close to each other in the prediction target space. We surprisingly find one simple yet effective idea: enforcing perceptual similarity during the dVAE training. Moreover, we adopt a self-supervised transformer model for deep feature extraction and show that it works well for calculating perceptual similarity.We demonstrate that such learned visual tokens indeed exhibit better semantic meanings, and help pre-training achieve superior transfer performance in various downstream tasks. For example, we achieve $\textbf{84.5\%}$ Top-1 accuracy on ImageNet-1K with ViT-B backbone, outperforming the competitive method BEiT by $\textbf{+1.3\%}$ under the same pre-training epochs. Our approach also gets significant improvement on object detection and segmentation on COCO and semantic segmentation on ADE20K. Equipped with a larger backbone ViT-H, we achieve the state-of-the-art ImageNet accuracy (\textbf{88.3\%}) among methods using only ImageNet-1K data.

Yinglin Zheng, Jianmin Bao, Dong Chen et al.

Although current face manipulation techniques achieve impressive performance regarding quality and controllability, they are struggling to generate temporal coherent face videos. In this work, we explore to take full advantage of the temporal coherence for video face forgery detection. To achieve this, we propose a novel end-to-end framework, which consists of two major stages. The first stage is a fully temporal convolution network (FTCN). The key insight of FTCN is to reduce the spatial convolution kernel size to 1, while maintaining the temporal convolution kernel size unchanged. We surprisingly find this special design can benefit the model for extracting the temporal features as well as improve the generalization capability. The second stage is a Temporal Transformer network, which aims to explore the long-term temporal coherence. The proposed framework is general and flexible, which can be directly trained from scratch without any pre-training models or external datasets. Extensive experiments show that our framework outperforms existing methods and remains effective when applied to detect new sorts of face forgery videos.

Zheyi Ma, Hao Li, Wen Fang et al.

To prevent the spread of coronavirus disease 2019 (COVID-19), preliminary temperature measurement and mask detection in public areas are conducted. However, the existing temperature measurement methods face the problems of safety and deployment. In this paper, to realize safe and accurate temperature measurement even when a person's face is partially obscured, we propose a cloud-edge-terminal collaborative system with a lightweight infrared temperature measurement model. A binocular camera with an RGB lens and a thermal lens is utilized to simultaneously capture image pairs. Then, a mobile detection model based on a multi-task cascaded convolutional network (MTCNN) is proposed to realize face alignment and mask detection on the RGB images. For accurate temperature measurement, we transform the facial landmarks on the RGB images to the thermal images by an affine transformation and select a more accurate temperature measurement area on the forehead. The collected information is uploaded to the cloud in real time for COVID-19 prevention. Experiments show that the detection model is only 6.1M and the average detection speed is 257ms. At a distance of 1m, the error of indoor temperature measurement is about 3%. That is, the proposed system can realize real-time temperature measurement in public areas.

Pan Zhang, Bo Zhang, Ting Zhang et al.

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in the pseudo supervision. In this work, we propose robust mutual learning that improves the prior approach in two aspects. First, the vanilla mutual learners suffer from the coupling issue that models may converge to learn homogeneous knowledge. We resolve this issue by introducing mean teachers to generate mutual supervisions so that there is no direct interaction between the two students. We also show that strong data augmentations, model noises and heterogeneous network architectures are essential to alleviate the model coupling. Second, we notice that mutual learning fails to leverage the network's own ability for pseudo label refinement. Therefore, we introduce self-rectification that leverages the internal knowledge and explicitly rectifies the pseudo labels before the mutual teaching. Such self-rectification and mutual teaching collaboratively improve the pseudo label accuracy throughout the learning. The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.

Yue Gao, Fangyun Wei, Jianmin Bao et al.

Cycle consistency is widely used for face editing. However, we observe that the generator tends to find a tricky way to hide information from the original image to satisfy the constraint of cycle consistency, making it impossible to maintain the rich details (e.g., wrinkles and moles) of non-editing areas. In this work, we propose a simple yet effective method named HifaFace to address the above-mentioned problem from two perspectives. First, we relieve the pressure of the generator to synthesize rich details by directly feeding the high-frequency information of the input image into the end of the generator. Second, we adopt an additional discriminator to encourage the generator to synthesize rich details. Specifically, we apply wavelet transformation to transform the image into multi-frequency domains, among which the high-frequency parts can be used to recover the rich details. We also notice that a fine-grained and wider-range control for the attribute is of great importance for face editing. To achieve this goal, we propose a novel attribute regression loss. Powered by the proposed framework, we achieve high-fidelity and arbitrary face editing, outperforming other state-of-the-art approaches.

Chulin Xie, Chuxin Wang, Bo Zhang et al.

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv to fully exploit the local structures as well as the global shape in point features. Secondly, we observe that the concatenation manner used by vanilla foldings limits its potential of generating a complex and faithful shape. Enlightened by the success of StyleGAN, we regard the shape feature as style code that modulates the normalization layers during the folding, which considerably enhances its capability. Thirdly, we realize that existing point supervisions, e.g., Chamfer Distance or Earth Mover's Distance, cannot faithfully reflect the perceptual quality of the reconstructed points. To address this, we propose to project the completed points to depth maps with a differentiable renderer and apply adversarial training to advocate the perceptual realism under different viewpoints. Comprehensive experiments on ShapeNet and KITTI prove the effectiveness of our method, which achieves state-of-the-art quantitative performance while offering superior visual quality.

Pan Zhang, Bo Zhang, Ting Zhang et al.

Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the discrepancy between source and target domains. In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation. In particular, we take one step further and exploit the feature distances from prototypes that provide richer information than mere prototypes. Specifically, we use it to estimate the likelihood of pseudo labels to facilitate online correction in the course of training. Meanwhile, we align the prototypical assignments based on relative feature distances for two different views of the same target, producing a more compact target feature space. Moreover, we find that distilling the already learned knowledge to a self-supervised pretrained model further boosts the performance. Our method shows tremendous performance advantage over state-of-the-art methods. We will make the code publicly available.

Xiaoyi Dong, Jianmin Bao, Dongdong Chen et al.

DeepFake detection has so far been dominated by ``artifact-driven'' methods and the detection performance significantly degrades when either the type of image artifacts is unknown or the artifacts are simply too hard to find. In this work, we present an alternative approach: Identity-Driven DeepFake Detection. Our approach takes as input the suspect image/video as well as the target identity information (a reference image or video). We output a decision on whether the identity in the suspect image/video is the same as the target identity. Our motivation is to prevent the most common and harmful DeepFakes that spread false information of a targeted person. The identity-based approach is fundamentally different in that it does not attempt to detect image artifacts. Instead, it focuses on whether the identity in the suspect image/video is true. To facilitate research on identity-based detection, we present a new large scale dataset ``Vox-DeepFake", in which each suspect content is associated with multiple reference images collected from videos of a target identity. We also present a simple identity-based detection algorithm called the OuterFace, which may serve as a baseline for further research. Even trained without fake videos, the OuterFace algorithm achieves superior detection accuracy and generalizes well to different DeepFake methods, and is robust with respect to video degradation techniques -- a performance not achievable with existing detection algorithms.

Xingran Zhou, Bo Zhang, Ting Zhang et al.

We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coarse level to guide the fine levels. At each hierarchy, the correspondence can be efficiently computed via PatchMatch that iteratively leverages the matchings from the neighborhood. Within each PatchMatch iteration, the ConvGRU module is employed to refine the current correspondence considering not only the matchings of larger context but also the historic estimates. The proposed CoCosNet v2, a GRU-assisted PatchMatch approach, is fully differentiable and highly efficient. When jointly trained with image translation, full-resolution semantic correspondence can be established in an unsupervised manner, which in turn facilitates the exemplar-based image translation. Experiments on diverse translation tasks show that CoCosNet v2 performs considerably better than state-of-the-art literature on producing high-resolution images.

Shuyang Gu, Jianmin Bao, Dong Chen et al.

Generative adversarial networks (GANs) have achieved rapid progress in learning rich data distributions. However, we argue about two main issues in existing techniques. First, the low quality problem where the learned distribution has massive low quality samples. Second, the missing modes problem where the learned distribution misses some certain regions of the real data distribution. To address these two issues, we propose a novel prior that captures the whole real data distribution for GANs, which are called PriorGANs. To be specific, we adopt a simple yet elegant Gaussian Mixture Model (GMM) to build an explicit probability distribution on the feature level for the whole real data. By maximizing the probability of generated data, we can push the low quality samples to high quality. Meanwhile, equipped with the prior, we can estimate the missing modes in the learned distribution and design a sampling strategy on the real data to solve the problem. The proposed real data prior can generalize to various training settings of GANs, such as LSGAN, WGAN-GP, SNGAN, and even the StyleGAN. Our experiments demonstrate that PriorGANs outperform the state-of-the-art on the CIFAR-10, FFHQ, LSUN-cat, and LSUN-bird datasets by large margins.

Yu Deng, Jiaolong Yang, Dong Chen et al.

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.

Sicheng Xu, Jiaolong Yang, Dong Chen et al.

In this paper, we present a learning-based approach for recovering the 3D geometry of human head from a single portrait image. Our method is learned in an unsupervised manner without any ground-truth 3D data. We represent the head geometry with a parametric 3D face model together with a depth map for other head regions including hair and ear. A two-step geometry learning scheme is proposed to learn 3D head reconstruction from in-the-wild face images, where we first learn face shape on single images using self-reconstruction and then learn hair and ear geometry using pairs of images in a stereo-matching fashion. The second step is based on the output of the first to not only improve the accuracy but also ensure the consistency of overall head geometry. We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images. We alter pose based on the recovered geometry and apply a refinement network trained with adversarial learning to ameliorate the reprojected images and translate them to the real image domain. Extensive evaluations and comparison with previous methods show that our new method can produce high-fidelity 3D head geometry and head pose manipulation results.

Ziyu Wan, Bo Zhang, Dongdong Chen et al.

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. And the translation between these two latent spaces is learned with synthetic paired data. This translation generalizes well to real photos because the domain gap is closed in the compact latent space. Besides, to address multiple degradations mixed in one old photo, we design a global branch with a partial nonlocal block targeting to the structured defects, such as scratches and dust spots, and a local branch targeting to the unstructured defects, such as noises and blurriness. Two branches are fused in the latent space, leading to improved capability to restore old photos from multiple defects. The proposed method outperforms state-of-the-art methods in terms of visual quality for old photos restoration.

Hao Li, Aozhou Wu, Wen Fang et al.

Resonant Beam Charging (RBC) is a wireless charging technology which supports multi-watt power transfer over meter-level distance. The features of safety, mobility and simultaneous charging capability enable RBC to charge multiple mobile devices safely at the same time. To detect the devices that need to be charged, a Mask R-CNN based dection model is proposed in previous work. However, considering the constraints of the RBC system, it's not easy to apply Mask R-CNN in lightweight hardware-embedded devices because of its heavy model and huge computation. Thus, we propose a machine learning detection approach which provides a lighter and faster model based on traditional Mask R-CNN. The proposed approach makes the object detection much easier to be transplanted on mobile devices and reduce the burden of hardware computation. By adjusting the structure of the backbone and the head part of Mask R-CNN, we reduce the average detection time from $1.02\mbox{s}$ per image to $0.6132\mbox{s}$, and reduce the model size from $245\mbox{MB}$ to $47.1\mbox{MB}$. The improved model is much more suitable for the application in the RBC system.

Pan Zhang, Bo Zhang, Dong Chen et al.

We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain (e.g., semantic segmentation mask, or edge map, or pose keypoints), given an exemplar image. The output has the style (e.g., color, texture) in consistency with the semantically corresponding objects in the exemplar. We propose to jointly learn the crossdomain correspondence and the image translation, where both tasks facilitate each other and thus can be learned with weak supervision. The images from distinct domains are first aligned to an intermediate domain where dense correspondence is established. Then, the network synthesizes images based on the appearance of semantically corresponding patches in the exemplar. We demonstrate the effectiveness of our approach in several image translation tasks. Our method is superior to state-of-the-art methods in terms of image quality significantly, with the image style faithful to the exemplar with semantic consistency. Moreover, we show the utility of our method for several applications

Shuyang Gu, Jianmin Bao, Dong Chen et al.

Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.

Lingzhi Li, Jianmin Bao, Ting Zhang et al.

In this paper we propose a novel image representation called face X-ray for detecting forgery in face images. The face X-ray of an input face image is a greyscale image that reveals whether the input image can be decomposed into the blending of two images from different sources. It does so by showing the blending boundary for a forged image and the absence of blending for a real image. We observe that most existing face manipulation methods share a common step: blending the altered face into an existing background image. For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms. Face X-ray is general in the sense that it only assumes the existence of a blending step and does not rely on any knowledge of the artifacts associated with a specific face manipulation technique. Indeed, the algorithm for computing face X-ray can be trained without fake images generated by any of the state-of-the-art face manipulation methods. Extensive experiments show that face X-ray remains effective when applied to forgery generated by unseen face manipulation techniques, while most existing face forgery detection or deepfake detection algorithms experience a significant performance drop.

Lingzhi Li, Jianmin Bao, Hao Yang et al.

In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.

Jinpeng Lin, Hao Yang, Dong Chen et al.

Face parsing computes pixel-wise label maps for different semantic components (e.g., hair, mouth, eyes) from face images. Existing face parsing literature have illustrated significant advantages by focusing on individual regions of interest (RoIs) for faces and facial components. However, the traditional crop-and-resize focusing mechanism ignores all contextual area outside the RoIs, and thus is not suitable when the component area is unpredictable, e.g. hair. Inspired by the physiological vision system of human, we propose a novel RoI Tanh-warping operator that combines the central vision and the peripheral vision together. It addresses the dilemma between a limited sized RoI for focusing and an unpredictable area of surrounding context for peripheral information. To this end, we propose a novel hybrid convolutional neural network for face parsing. It uses hierarchical local based method for inner facial components and global methods for outer facial components. The whole framework is simple and principled, and can be trained end-to-end. To facilitate future research of face parsing, we also manually relabel the training data of the HELEN dataset and will make it public. Experiments on both HELEN and LFW-PL benchmarks demonstrate that our method surpasses state-of-the-art methods.

Shuyang Gu, Jianmin Bao, Hao Yang et al.

Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to better correspondences for image translation, and local face editing. With the mask, our network is available to many applications, like face synthesis driven by mask, face Swap+ (including hair in swapping), and local manipulation. It can also boost the performance of face parsing a bit as an option of data augmentation.

Jianmin Bao, Dong Chen, Fang Wen et al.

We propose a framework based on Generative Adversarial Networks to disentangle the identity and attributes of faces, such that we can conveniently recombine different identities and attributes for identity preserving face synthesis in open domains. Previous identity preserving face synthesis processes are largely confined to synthesizing faces with known identities that are already in the training dataset. To synthesize a face with identity outside the training dataset, our framework requires one input image of that subject to produce an identity vector, and any other input face image to extract an attribute vector capturing, e.g., pose, emotion, illumination, and even the background. We then recombine the identity vector and the attribute vector to synthesize a new face of the subject with the extracted attribute. Our proposed framework does not need to annotate the attributes of faces in any way. It is trained with an asymmetric loss function to better preserve the identity and stabilize the training process. It can also effectively leverage large amounts of unlabeled training face images to further improve the fidelity of the synthesized faces for subjects that are not presented in the labeled training face dataset. Our experiments demonstrate the efficacy of the proposed framework. We also present its usage in a much broader set of applications including face frontalization, face attribute morphing, and face adversarial example detection.

Jianmin Bao, Dong Chen, Fang Wen et al.

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a specific person or objects in a category. Our approach models an image as a composition of label and latent attributes in a probabilistic model. By varying the fine-grained category label fed into the resulting generative model, we can generate images in a specific category with randomly drawn values on a latent attribute vector. Our approach has two novel aspects. First, we adopt a cross entropy loss for the discriminative and classifier network, but a mean discrepancy objective for the generative network. This kind of asymmetric loss function makes the GAN training more stable. Second, we adopt an encoder network to learn the relationship between the latent space and the real image space, and use pairwise feature matching to keep the structure of generated images. We experiment with natural images of faces, flowers, and birds, and demonstrate that the proposed models are capable of generating realistic and diverse samples with fine-grained category labels. We further show that our models can be applied to other tasks, such as image inpainting, super-resolution, and data augmentation for training better face recognition models.

Dong Chen, Gang Hua, Fang Wen et al.

Large pose variations remain to be a challenge that confronts real-word face detection. We propose a new cascaded Convolutional Neural Network, dubbed the name Supervised Transformer Network, to address this challenge. The first stage is a multi-task Region Proposal Network (RPN), which simultaneously predicts candidate face regions along with associated facial landmarks. The candidate regions are then warped by mapping the detected facial landmarks to their canonical positions to better normalize the face patterns. The second stage, which is a RCNN, then verifies if the warped candidate regions are valid faces or not. We conduct end-to-end learning of the cascaded network, including optimizing the canonical positions of the facial landmarks. This supervised learning of the transformations automatically selects the best scale to differentiate face/non-face patterns. By combining feature maps from both stages of the network, we achieve state-of-the-art detection accuracies on several public benchmarks. For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector. Our detector runs at 30 FPS on a single CPU core for a VGA-resolution image.

Jiaolong Yang, Peiran Ren, Dongqing Zhang et al.

This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spanned by them. Due to the attention mechanism, the aggregation is invariant to the image order. Our NAN is trained with a standard classification or verification loss without any extra supervision signal, and we found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces. The experiments on IJB-A, YouTube Face, Celebrity-1000 video face recognition benchmarks show that it consistently outperforms naive aggregation methods and achieves the state-of-the-art accuracy.