Xiaoou Tang

Qihuang Zhong, Liang Ding, Yibing Zhan et al.

This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight difficult language understanding tasks, including question answering, natural language inference, word sense disambiguation, coreference resolution, and reasoning. [Method] Instead of arbitrarily increasing the size of a pretrained language model (PLM), our aim is to 1) fully extract knowledge from the input pretraining data given a certain parameter budget, e.g., 6B, and 2) effectively transfer this knowledge to downstream tasks. To achieve goal 1), we propose self-evolution learning for PLMs to wisely predict the informative tokens that should be masked, and supervise the masked language modeling (MLM) process with rectified smooth labels. For goal 2), we leverage the prompt transfer technique to improve the low-resource tasks by transferring the knowledge from the foundation model and related downstream tasks to the target task. [Results] According to our submission record (Oct. 2022), with our optimized pretraining and fine-tuning strategies, our 6B Vega method achieved new state-of-the-art performance on 4/8 tasks, sitting atop the SuperGLUE leaderboard on Oct. 8, 2022, with an average score of 91.3.

Xingang Pan, Xiaohang Zhan, Jianping Shi et al.

Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods. SW learns to switch among these operations in an end-to-end manner. It has several advantages. First, SW adaptively selects appropriate whitening or standardization statistics for different tasks (see Fig.1), making it well suited for a wide range of tasks without manual design. Second, by integrating benefits of different normalizers, SW shows consistent improvements over its counterparts in various challenging benchmarks. Third, SW serves as a useful tool for understanding the characteristics of whitening and standardization techniques. We show that SW outperforms other alternatives on image classification (CIFAR-10/100, ImageNet), semantic segmentation (ADE20K, Cityscapes), domain adaptation (GTA5, Cityscapes), and image style transfer (COCO). For example, without bells and whistles, we achieve state-of-the-art performance with 45.33% mIoU on the ADE20K dataset. Code is available at https://github.com/XingangPan/Switchable-Whitening.

Tak-Wai Hui, Xiaoou Tang, Chen Change Loy

Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (CNN) and have showed promising results. FlowNet2, the state-of-the-art CNN, requires over 160M parameters to achieve accurate flow estimation. Our LiteFlowNet2 outperforms FlowNet2 on Sintel and KITTI benchmarks, while being 25.3 times smaller in the model size and 3.1 times faster in the running speed. LiteFlowNet2 is built on the foundation laid by conventional methods and resembles the corresponding roles as data fidelity and regularization in variational methods. We compute optical flow in a spatial-pyramid formulation as SPyNet but through a novel lightweight cascaded flow inference. It provides high flow estimation accuracy through early correction with seamless incorporation of descriptor matching. Flow regularization is used to ameliorate the issue of outliers and vague flow boundaries through feature-driven local convolutions. Our network also owns an effective structure for pyramidal feature extraction and embraces feature warping rather than image warping as practiced in FlowNet2 and SPyNet. Comparing to LiteFlowNet, LiteFlowNet2 improves the optical flow accuracy on Sintel Clean by 23.3%, Sintel Final by 12.8%, KITTI 2012 by 19.6%, and KITTI 2015 by 18.8%, while being 2.2 times faster. Our network protocol and trained models are made publicly available on https://github.com/twhui/LiteFlowNet2.

Xintao Wang, Ke Yu, Shixiang Wu et al.

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge. The code is available at https://github.com/xinntao/ESRGAN .

Tak-Wai Hui, Xiaoou Tang, Chen Change Loy

FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on the challenging Sintel final pass and KITTI benchmarks, while being 30 times smaller in the model size and 1.36 times faster in the running speed. This is made possible by drilling down to architectural details that might have been missed in the current frameworks: (1) We present a more effective flow inference approach at each pyramid level through a lightweight cascaded network. It not only improves flow estimation accuracy through early correction, but also permits seamless incorporation of descriptor matching in our network. (2) We present a novel flow regularization layer to ameliorate the issue of outliers and vague flow boundaries by using a feature-driven local convolution. (3) Our network owns an effective structure for pyramidal feature extraction and embraces feature warping rather than image warping as practiced in FlowNet2. Our code and trained models are available at https://github.com/twhui/LiteFlowNet .

Yu Liu, Hongyang Li, Junjie Yan et al.

Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map at a particular scale, it generates the prediction at a smaller scale that is half the size of input. To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid. (b): propose a landmark retracing network (LRN) to trace back locations of the regressed landmarks and generate a confidence score for each landmark; LRN can effectively alleviate false positives caused by the accumulated error in RSA. The whole system can be trained end-to-end in a unified CNN framework. Experiments demonstrate that our proposed algorithm is superior against state-of-the-art methods on face detection benchmarks and achieves comparable results for generic proposal generation. The source code of RSA is available at github.com/sciencefans/RSA-for-object-detection.

Yujun Shen, Ceyuan Yang, Xiaoou Tang et al.

Although Generative Adversarial Networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a random code to a photo-realistic image. In this work, we propose a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space. We first find that GANs learn various semantics in some linear subspaces of the latent space. After identifying these subspaces, we can realistically manipulate the corresponding facial attributes without retraining the model. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection, resulting in more precise control of the attribute manipulation. Besides manipulating the gender, age, expression, and presence of eyeglasses, we can even alter the face pose and fix the artifacts accidentally made by GANs. Furthermore, we perform an in-depth face identity analysis and a layer-wise analysis to evaluate the editing results quantitatively. Finally, we apply our approach to real face editing by employing GAN inversion approaches and explicitly training feed-forward models based on the synthetic data established by InterFaceGAN. Extensive experimental results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable face representation.

Yujun Shen, Jinjin Gu, Xiaoou Tang et al.

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image. Previous work assumes the latent space learned by GANs follows a distributed representation but observes the vector arithmetic phenomenon. In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs. In this framework, we conduct a detailed study on how different semantics are encoded in the latent space of GANs for face synthesis. We find that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations. We explore the disentanglement between various semantics and manage to decouple some entangled semantics with subspace projection, leading to more precise control of facial attributes. Besides manipulating gender, age, expression, and the presence of eyeglasses, we can even vary the face pose as well as fix the artifacts accidentally generated by GAN models. The proposed method is further applied to achieve real image manipulation when combined with GAN inversion methods or some encoder-involved models. Extensive results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable facial attribute representation.

Ke Yu, Xintao Wang, Chao Dong et al.

Very deep Convolutional Neural Networks (CNNs) have greatly improved the performance on various image restoration tasks. However, this comes at a price of increasing computational burden, hence limiting their practical usages. We observe that some corrupted image regions are inherently easier to restore than others since the distortion and content vary within an image. To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region. We train the pathfinder using reinforcement learning with a difficulty-regulated reward. This reward is related to the performance, complexity and "the difficulty of restoring a region". A policy mask is further investigated to jointly process all the image regions. We conduct experiments on denoising and mixed restoration tasks. The results show that our method achieves comparable or superior performance to existing approaches with less computational cost. In particular, Path-Restore is effective for real-world denoising, where the noise distribution varies across different regions on a single image. Compared to the state-of-the-art RIDNet, our method achieves comparable performance and runs 2.7x faster on the realistic Darmstadt Noise Dataset.

Yuying Ge, Ruimao Zhang, Lingyun Wu et al.

Understanding fashion images has been advanced by benchmarks with rich annotations such as DeepFashion, whose labels include clothing categories, landmarks, and consumer-commercial image pairs. However, DeepFashion has nonnegligible issues such as single clothing-item per image, sparse landmarks (4~8 only), and no per-pixel masks, making it had significant gap from real-world scenarios. We fill in the gap by presenting DeepFashion2 to address these issues. It is a versatile benchmark of four tasks including clothes detection, pose estimation, segmentation, and retrieval. It has 801K clothing items where each item has rich annotations such as style, scale, viewpoint, occlusion, bounding box, dense landmarks and masks. There are also 873K Commercial-Consumer clothes pairs. A strong baseline is proposed, called Match R-CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner. Extensive evaluations are conducted with different criterions in DeepFashion2.

Mengya Gao, Yujun Shen, Quanquan Li et al.

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and the KD loss simultaneously, using a pre-defined loss weight to balance these two terms. In this work, we propose to first transfer the backbone knowledge from a teacher to the student, and then only learn the task-head of the student network. Such a decomposition of the training process circumvents the need of choosing an appropriate loss weight, which is often difficult in practice, and thus makes it easier to apply to different datasets and tasks. Importantly, the decomposition permits the core of our method, Stage-by-Stage Knowledge Distillation (SSKD), which facilitates progressive feature mimicking from teacher to student. Extensive experiments on CIFAR-100 and ImageNet suggest that SSKD significantly narrows down the performance gap between student and teacher, outperforming state-of-the-art approaches. We also demonstrate the generalization ability of SSKD on other challenging benchmarks, including face recognition on IJB-A dataset as well as object detection on COCO dataset.

Yujun Shen, Bolei Zhou, Ping Luo et al.

The advance of Generative Adversarial Networks (GANs) enables realistic face image synthesis. However, synthesizing face images that preserve facial identity as well as have high diversity within each identity remains challenging. To address this problem, we present FaceFeat-GAN, a novel generative model that improves both image quality and diversity by using two stages. Unlike existing single-stage models that map random noise to image directly, our two-stage synthesis includes the first stage of diverse feature generation and the second stage of feature-to-image rendering. The competitions between generators and discriminators are carefully designed in both stages with different objective functions. Specially, in the first stage, they compete in the feature domain to synthesize various facial features rather than images. In the second stage, they compete in the image domain to render photo-realistic images that contain high diversity but preserve identity. Extensive experiments show that FaceFeat-GAN generates images that not only retain identity information but also have high diversity and quality, significantly outperforming previous methods.

Xintao Wang, Ke Yu, Chao Dong et al.

Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect. However, the large variety of user flavors motivates the possibility of continuous transition among different output effects. Unlike existing methods that require a specific design to achieve one particular transition (e.g., style transfer), we propose a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer. Specifically, our method, namely Deep Network Interpolation (DNI), applies linear interpolation in the parameter space of two or more correlated networks. A smooth control of imagery effects can be achieved by tweaking the interpolation coefficients. In addition to DNI and its broad applications, we also investigate the mechanism of network interpolation from the perspective of learned filters.

Yubin Deng, Ke Yu, Dahua Lin et al.

Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a particular action performed by an agent. However, tasks with sparse reward signals are still challenging to on-policy methods. In this paper, we introduce an effective characterization of past reward statistics (which can be seen as long-term feedback signals) to supplement this immediate reward feedback. In particular, value functions are learned with multi-critics supervision, enabling complex value functions to be more easily approximated in on-policy learning, even when the reward signals are sparse. We also introduce a novel exploration mechanism called "hot-wiring" that can give a boost to seemingly trapped agents. We demonstrate the effectiveness of our advantage actor multi-critic (A2MC) method across the discrete domains in Atari games as well as continuous domains in the MuJoCo environments. A video demo is provided at https://youtu.be/zBmpf3Yz8tc.

Xingang Pan, Ping Luo, Jianping Shi et al.

Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IBN-Net, a novel convolutional architecture, which remarkably enhances a CNN's modeling ability on one domain (e.g. Cityscapes) as well as its generalization capacity on another domain (e.g. GTA5) without finetuning. IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances. This work has three key contributions. (1) By delving into IN and BN, we disclose that IN learns features that are invariant to appearance changes, such as colors, styles, and virtuality/reality, while BN is essential for preserving content related information. (2) IBN-Net can be applied to many advanced deep architectures, such as DenseNet, ResNet, ResNeXt, and SENet, and consistently improve their performance without increasing computational cost. (3) When applying the trained networks to new domains, e.g. from GTA5 to Cityscapes, IBN-Net achieves comparable improvements as domain adaptation methods, even without using data from the target domain. With IBN-Net, we won the 1st place on the WAD 2018 Challenge Drivable Area track, with an mIoU of 86.18%.

Chen Huang, Yining Li, Chen Change Loy et al.

Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep learning methods typically follow classic strategies such as class re-sampling or cost-sensitive training. In this paper, we conduct extensive and systematic experiments to validate the effectiveness of these classic schemes for representation learning on class-imbalanced data. We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain inter-cluster margins both within and between classes. This tight constraint effectively reduces the class imbalance inherent in the local data neighborhood, thus carving much more balanced class boundaries locally. We show that it is easy to deploy angular margins between the cluster distributions on a hypersphere manifold. Such learned Cluster-based Large Margin Local Embedding (CLMLE), when combined with a simple k-nearest cluster algorithm, shows significant improvements in accuracy over existing methods on both face recognition and face attribute prediction tasks that exhibit imbalanced class distribution.

Kaidi Cao, Yu Rong, Cheng Li et al.

Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead.

Xingang Pan, Xiaohang Zhan, Jianping Shi et al.

Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored. These relationships are important to learn semantic objects with strong shape priors but weak appearance coherences, such as traffic lanes, which are often occluded or not even painted on the road surface as shown in Fig. 1 (a). In this paper, we propose Spatial CNN (SCNN), which generalizes traditional deep layer-by-layer convolutions to slice-byslice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer. Such SCNN is particular suitable for long continuous shape structure or large objects, with strong spatial relationship but less appearance clues, such as traffic lanes, poles, and wall. We apply SCNN on a newly released very challenging traffic lane detection dataset and Cityscapse dataset. The results show that SCNN could learn the spatial relationship for structure output and significantly improves the performance. We show that SCNN outperforms the recurrent neural network (RNN) based ReNet and MRF+CNN (MRFNet) in the lane detection dataset by 8.7% and 4.6% respectively. Moreover, our SCNN won the 1st place on the TuSimple Benchmark Lane Detection Challenge, with an accuracy of 96.53%.

Xiaohang Zhan, Ziwei Liu, Ping Luo et al.

Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g. ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently proposed to pre-train a network without any human-provided labels. The key of this new form of learning is to design a proxy task (e.g. image colorization), from which a discriminative loss can be formulated on unlabeled data. Many proxy tasks, however, lack the critical supervision signals that could induce discriminative representation for the target image segmentation task. Thus self-supervision's performance is still far from that of supervised pre-training. In this study, we overcome this limitation by incorporating a "mix-and-match" (M&M) tuning stage in the self-supervision pipeline. The proposed approach is readily pluggable to many self-supervision methods and does not use more annotated samples than the original process. Yet, it is capable of boosting the performance of target image segmentation task to surpass fully-supervised pre-trained counterpart. The improvement is made possible by better harnessing the limited pixel-wise annotations in the target dataset. Specifically, we first introduce the "mix" stage, which sparsely samples and mixes patches from the target set to reflect rich and diverse local patch statistics of target images. A "match" stage then forms a class-wise connected graph, which can be used to derive a strong triplet-based discriminative loss for fine-tuning the network. Our paradigm follows the standard practice in existing self-supervised studies and no extra data or label is required. With the proposed M&M approach, for the first time, a self-supervision method can achieve comparable or even better performance compared to its ImageNet pre-trained counterpart on both PASCAL VOC2012 dataset and CityScapes dataset.

Yining Li, Chen Huang, Xiaoou Tang et al.

The ability to ask questions is a powerful tool to gather information in order to learn about the world and resolve ambiguities. In this paper, we explore a novel problem of generating discriminative questions to help disambiguate visual instances. Our work can be seen as a complement and new extension to the rich research studies on image captioning and question answering. We introduce the first large-scale dataset with over 10,000 carefully annotated images-question tuples to facilitate benchmarking. In particular, each tuple consists of a pair of images and 4.6 discriminative questions (as positive samples) and 5.9 non-discriminative questions (as negative samples) on average. In addition, we present an effective method for visual discriminative question generation. The method can be trained in a weakly supervised manner without discriminative images-question tuples but just existing visual question answering datasets. Promising results are shown against representative baselines through quantitative evaluations and user studies.

Sijie Yan, Ziwei Liu, Ping Luo et al.

Fashion landmarks are functional key points defined on clothes, such as corners of neckline, hemline, and cuff. They have been recently introduced as an effective visual representation for fashion image understanding. However, detecting fashion landmarks are challenging due to background clutters, human poses, and scales. To remove the above variations, previous works usually assumed bounding boxes of clothes are provided in training and test as additional annotations, which are expensive to obtain and inapplicable in practice. This work addresses unconstrained fashion landmark detection, where clothing bounding boxes are not provided in both training and test. To this end, we present a novel Deep LAndmark Network (DLAN), where bounding boxes and landmarks are jointly estimated and trained iteratively in an end-to-end manner. DLAN contains two dedicated modules, including a Selective Dilated Convolution for handling scale discrepancies, and a Hierarchical Recurrent Spatial Transformer for handling background clutters. To evaluate DLAN, we present a large-scale fashion landmark dataset, namely Unconstrained Landmark Database (ULD), consisting of 30K images. Statistics show that ULD is more challenging than existing datasets in terms of image scales, background clutters, and human poses. Extensive experiments demonstrate the effectiveness of DLAN over the state-of-the-art methods. DLAN also exhibits excellent generalization across different clothing categories and modalities, making it extremely suitable for real-world fashion analysis.

Xiaoxiao Li, Yuankai Qi, Zhe Wang et al.

Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an effective mechanism to prevent the target from being lost via adaptive object re-identification. Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module. The former module produces an initial probability map by flow warping while the latter module retrieves missing instances by adaptive matching. With these two modules iteratively applied, our VS-ReID records a global mean (Region Jaccard and Boundary F measure) of 0.699, the best performance in 2017 DAVIS Challenge.

Yubin Deng, Chen Change Loy, Xiaoou Tang

We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive annotations in the form of aligned image pairs. In contrast to these approaches, our proposed EnhanceGAN only requires weak supervision (binary labels on image aesthetic quality) and is able to learn enhancement operators for the task of aesthetic-based image enhancement. In particular, we show the effectiveness of a piecewise color enhancement module trained with weak supervision, and extend the proposed EnhanceGAN framework to learning a deep filtering-based aesthetic enhancer. The full differentiability of our image enhancement operators enables the training of EnhanceGAN in an end-to-end manner. We further demonstrate the capability of EnhanceGAN in learning aesthetic-based image cropping without any groundtruth cropping pairs. Our weakly-supervised EnhanceGAN reports competitive quantitative results on aesthetic-based color enhancement as well as automatic image cropping, and a user study confirms that our image enhancement results are on par with or even preferred over professional enhancement.

Shuo Yang, Yuanjun Xiong, Chen Change Loy et al.

In this paper, we share our experience in designing a convolutional network-based face detector that could handle faces of an extremely wide range of scales. We show that faces with different scales can be modeled through a specialized set of deep convolutional networks with different structures. These detectors can be seamlessly integrated into a single unified network that can be trained end-to-end. In contrast to existing deep models that are designed for wide scale range, our network does not require an image pyramid input and the model is of modest complexity. Our network, dubbed ScaleFace, achieves promising performance on WIDER FACE and FDDB datasets with practical runtime speed. Specifically, our method achieves 76.4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.

Limin Wang, Yuanjun Xiong, Zhe Wang et al.

Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structures with a new segment-based sampling and aggregation module. This unique design enables our TSN to efficiently learn action models by using the whole action videos. The learned models could be easily adapted for action recognition in both trimmed and untrimmed videos with simple average pooling and multi-scale temporal window integration, respectively. We also study a series of good practices for the instantiation of TSN framework given limited training samples. Our approach obtains the state-the-of-art performance on four challenging action recognition benchmarks: HMDB51 (71.0%), UCF101 (94.9%), THUMOS14 (80.1%), and ActivityNet v1.2 (89.6%). Using the proposed RGB difference for motion models, our method can still achieve competitive accuracy on UCF101 (91.0%) while running at 340 FPS. Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.

Fei Wang, Mengqing Jiang, Chen Qian et al.

In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Attention Network is built by stacking Attention Modules which generate attention-aware features. The attention-aware features from different modules change adaptively as layers going deeper. Inside each Attention Module, bottom-up top-down feedforward structure is used to unfold the feedforward and feedback attention process into a single feedforward process. Importantly, we propose attention residual learning to train very deep Residual Attention Networks which can be easily scaled up to hundreds of layers. Extensive analyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the effectiveness of every module mentioned above. Our Residual Attention Network achieves state-of-the-art object recognition performance on three benchmark datasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and ImageNet (4.8% single model and single crop, top-5 error). Note that, our method achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69% forward FLOPs comparing to ResNet-200. The experiment also demonstrates that our network is robust against noisy labels.

Yue Zhao, Yuanjun Xiong, Limin Wang et al.

Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. This allows the framework to effectively distinguish positive proposals from background or incomplete ones, thus leading to both accurate recognition and localization. These components are integrated into a unified network that can be efficiently trained in an end-to-end fashion. Additionally, a simple yet effective temporal action proposal scheme, dubbed temporal actionness grouping (TAG) is devised to generate high quality action proposals. On two challenging benchmarks, THUMOS14 and ActivityNet, our method remarkably outperforms previous state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling actions with various temporal structures.

Xiaoxiao Li, Ziwei Liu, Ping Luo et al.

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a cascade of several sub-models. Earlier sub-models are trained to handle easy and confident regions, and they progressively feed-forward harder regions to the next sub-model for processing. Convolutions are only calculated on these regions to reduce computations. The proposed method possesses several advantages. First, LC classifies most of the easy regions in the shallow stage and makes deeper stage focuses on a few hard regions. Such an adaptive and 'difficulty-aware' learning improves segmentation performance. Second, LC accelerates both training and testing of deep network thanks to early decisions in the shallow stage. Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models. We evaluate our method on PASCAL VOC and Cityscapes datasets, achieving state-of-the-art performance and fast speed.

Yuanjun Xiong, Yue Zhao, Limin Wang et al.

Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and completeness of a candidate instance. On two challenging temporal activity detection datasets, THUMOS14 and ActivityNet, the proposed framework significantly outperforms the existing state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling activities with various temporal structures.

Ziwei Liu, Raymond A. Yeh, Xiaoou Tang et al.

We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions often fail where flow estimation is challenging, while newer neural-network-based methods that hallucinate pixel values directly often produce blurry results. We combine the advantages of these two methods by training a deep network that learns to synthesize video frames by flowing pixel values from existing ones, which we call deep voxel flow. Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. The technique is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-of-the-art.

Shuo Yang, Ping Luo, Chen Change Loy et al.

We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is data-driven, and carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variations. Our method achieves promising performance on popular benchmarks including FDDB, PASCAL Faces, AFW, and WIDER FACE.

Chen Huang, Chen Change Loy, Xiaoou Tang

Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric. To make learning more effective and efficient, hard sample mining is usually employed, with samples identified through computing the Euclidean feature distance. However, the global Euclidean distance cannot faithfully characterize the true feature similarity in a complex visual feature space, where the intraclass distance in a high-density region may be larger than the interclass distance in low-density regions. In this paper, we introduce a Position-Dependent Deep Metric (PDDM) unit, which is capable of learning a similarity metric adaptive to local feature structure. The metric can be used to select genuinely hard samples in a local neighborhood to guide the deep embedding learning in an online and robust manner. The new layer is appealing in that it is pluggable to any convolutional networks and is trained end-to-end. Our local similarity-aware feature embedding not only demonstrates faster convergence and boosted performance on two complex image retrieval datasets, its large margin nature also leads to superior generalization results under the large and open set scenarios of transfer learning and zero-shot learning on ImageNet 2010 and ImageNet-10K datasets.

Yubin Deng, Chen Change Loy, Xiaoou Tang

This survey aims at reviewing recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality photos from low-quality ones based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature trying to solve this challenging problem. In this survey, we present a systematic listing of the reviewed approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (dataset characteristics and evaluation metrics). Main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep learning techniques, we systematically evaluate recent deep learning settings that are useful for developing a robust deep model for aesthetic scoring. Experiments are conducted using simple yet solid baselines that are competitive with the current state-of-the-arts. Moreover, we discuss the possibility of manipulating the aesthetics of images through computational approaches. We hope that our survey could serve as a comprehensive reference source for future research on the study of image aesthetic assessment.

Zhanpeng Zhang, Ping Luo, Chen Change Loy et al.

Interpersonal relation defines the association, e.g., warm, friendliness, and dominance, between two or more people. Motivated by psychological studies, we investigate if such fine-grained and high-level relation traits can be characterized and quantified from face images in the wild. We address this challenging problem by first studying a deep network architecture for robust recognition of facial expressions. Unlike existing models that typically learn from facial expression labels alone, we devise an effective multitask network that is capable of learning from rich auxiliary attributes such as gender, age, and head pose, beyond just facial expression data. While conventional supervised training requires datasets with complete labels (e.g., all samples must be labeled with gender, age, and expression), we show that this requirement can be relaxed via a novel attribute propagation method. The approach further allows us to leverage the inherent correspondences between heterogeneous attribute sources despite the disparate distributions of different datasets. With the network we demonstrate state-of-the-art results on existing facial expression recognition benchmarks. To predict inter-personal relation, we use the expression recognition network as branches for a Siamese model. Extensive experiments show that our model is capable of mining mutual context of faces for accurate fine-grained interpersonal prediction.

Zhirong Wu, Dahua Lin, Xiaoou Tang

Markov Random Fields (MRFs), a formulation widely used in generative image modeling, have long been plagued by the lack of expressive power. This issue is primarily due to the fact that conventional MRFs formulations tend to use simplistic factors to capture local patterns. In this paper, we move beyond such limitations, and propose a novel MRF model that uses fully-connected neurons to express the complex interactions among pixels. Through theoretical analysis, we reveal an inherent connection between this model and recurrent neural networks, and thereon derive an approximated feed-forward network that couples multiple RNNs along opposite directions. This formulation combines the expressive power of deep neural networks and the cyclic dependency structure of MRF in a unified model, bringing the modeling capability to a new level. The feed-forward approximation also allows it to be efficiently learned from data. Experimental results on a variety of low-level vision tasks show notable improvement over state-of-the-arts.

Ziwei Liu, Sijie Yan, Ping Luo et al.

Visual fashion analysis has attracted many attentions in the recent years. Previous work represented clothing regions by either bounding boxes or human joints. This work presents fashion landmark detection or fashion alignment, which is to predict the positions of functional key points defined on the fashion items, such as the corners of neckline, hemline, and cuff. To encourage future studies, we introduce a fashion landmark dataset with over 120K images, where each image is labeled with eight landmarks. With this dataset, we study fashion alignment by cascading multiple convolutional neural networks in three stages. These stages gradually improve the accuracies of landmark predictions. Extensive experiments demonstrate the effectiveness of the proposed method, as well as its generalization ability to pose estimation. Fashion landmark is also compared to clothing bounding boxes and human joints in two applications, fashion attribute prediction and clothes retrieval, showing that fashion landmark is a more discriminative representation to understand fashion images.

Ke Yu, Chao Dong, Chen Change Loy et al.

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened images that are accompanied with ringing effects. Inspired by the success of deep convolutional networks (DCN) on superresolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. To meet the speed requirement of real-world applications, we further accelerate the proposed baseline model by layer decomposition and joint use of large-stride convolutional and deconvolutional layers. This also leads to a more general CNN framework that has a close relationship with the conventional Multi-Layer Perceptron (MLP). Finally, the modified network achieves a speed up of 7.5 times with almost no performance loss compared to the baseline model. We also demonstrate that a deeper model can be effectively trained with features learned in a shallow network. Following a similar "easy to hard" idea, we systematically investigate three practical transfer settings and show the effectiveness of transfer learning in low-level vision problems. Our method shows superior performance than the state-of-the-art methods both on benchmark datasets and a real-world use case.

Limin Wang, Yuanjun Xiong, Zhe Wang et al.

Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles to design effective ConvNet architectures for action recognition in videos and learn these models given limited training samples. Our first contribution is temporal segment network (TSN), a novel framework for video-based action recognition. which is based on the idea of long-range temporal structure modeling. It combines a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video. The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network. Our approach obtains the state-the-of-art performance on the datasets of HMDB51 ( $ 69.4\% $) and UCF101 ($ 94.2\% $). We also visualize the learned ConvNet models, which qualitatively demonstrates the effectiveness of temporal segment network and the proposed good practices.

Yuanjun Xiong, Limin Wang, Zhe Wang et al.

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal segment networks and further raise the performance via a number of other techniques. Specifically, we use the latest deep model architecture, e.g., ResNet and Inception V3, and introduce new aggregation schemes (top-k and attention-weighted pooling). Additionally, we incorporate the audio as a complementary channel, extracting relevant information via a CNN applied to the spectrograms. With these techniques, we derive an ensemble of deep models, which, together, attains a high classification accuracy (mAP $93.23\%$) on the testing set and secured the first place in the challenge.

Chao Dong, Chen Change Loy, Xiaoou Tang

As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors.

Shizhan Zhu, Sifei Liu, Chen Change Loy et al.

We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landmarks localization or dense correspondence field), we alternatingly optimize two complementary tasks, namely face hallucination and dense correspondence field estimation, in a unified framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details. Extensive experiments demonstrate that such formulation allows exceptional hallucination quality on in-the-wild low-res faces with significant pose and illumination variations.

Ziwei Liu, Xiaoxiao Li, Ping Luo et al.

Semantic segmentation tasks can be well modeled by Markov Random Field (MRF). This paper addresses semantic segmentation by incorporating high-order relations and mixture of label contexts into MRF. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN to model unary terms and additional layers are devised to approximate the mean field (MF) algorithm for pairwise terms. It has several appealing properties. First, different from the recent works that required many iterations of MF during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing models as its special cases. Furthermore, pairwise terms in DPN provide a unified framework to encode rich contextual information in high-dimensional data, such as images and videos. Third, DPN makes MF easier to be parallelized and speeded up, thus enabling efficient inference. DPN is thoroughly evaluated on standard semantic image/video segmentation benchmarks, where a single DPN model yields state-of-the-art segmentation accuracies on PASCAL VOC 2012, Cityscapes dataset and CamVid dataset.

Limin Wang, Yu Qiao, Xiaoou Tang et al.

Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as action recognition and action detection. This paper presents a new deep architecture for actionness estimation, called hybrid fully convolutional network (H-FCN), which is composed of appearance FCN (A-FCN) and motion FCN (M-FCN). These two FCNs leverage the strong capacity of deep models to estimate actionness maps from the perspectives of static appearance and dynamic motion, respectively. In addition, the fully convolutional nature of H-FCN allows it to efficiently process videos with arbitrary sizes. Experiments are conducted on the challenging datasets of Stanford40, UCF Sports, and JHMDB to verify the effectiveness of H-FCN on actionness estimation, which demonstrate that our method achieves superior performance to previous ones. Moreover, we apply the estimated actionness maps on action proposal generation and action detection. Our actionness maps advance the current state-of-the-art performance of these tasks substantially.

Chen Huang, Chen Change Loy, Xiaoou Tang

Data imbalance is common in many vision tasks where one or more classes are rare. Without addressing this issue conventional methods tend to be biased toward the majority class with poor predictive accuracy for the minority class. These methods further deteriorate on small, imbalanced data that has a large degree of class overlap. In this study, we propose a novel discriminative sparse neighbor approximation (DSNA) method to ameliorate the effect of class-imbalance during prediction. Specifically, given a test sample, we first traverse it through a cost-sensitive decision forest to collect a good subset of training examples in its local neighborhood. Then we generate from this subset several class-discriminating but overlapping clusters and model each as an affine subspace. From these subspaces, the proposed DSNA iteratively seeks an optimal approximation of the test sample and outputs an unbiased prediction. We show that our method not only effectively mitigates the imbalance issue, but also allows the prediction to extrapolate to unseen data. The latter capability is crucial for achieving accurate prediction on small dataset with limited samples. The proposed imbalanced learning method can be applied to both classification and regression tasks at a wide range of imbalance levels. It significantly outperforms the state-of-the-art methods that do not possess an imbalance handling mechanism, and is found to perform comparably or even better than recent deep learning methods by using hand-crafted features only.

Yi Sun, Xiaogang Wang, Xiaoou Tang

This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition. The sparse ConvNets are learned in an iterative way, each time one additional layer is sparsified and the entire model is re-trained given the initial weights learned in previous iterations. One important finding is that directly training the sparse ConvNet from scratch failed to find good solutions for face recognition, while using a previously learned denser model to properly initialize a sparser model is critical to continue learning effective features for face recognition. This paper also proposes a new neural correlation-based weight selection criterion and empirically verifies its effectiveness in selecting informative connections from previously learned models in each iteration. When taking a moderately sparse structure (26%-76% of weights in the dense model), the proposed sparse ConvNet model significantly improves the face recognition performance of the previous state-of-the-art DeepID2+ models given the same training data, while it keeps the performance of the baseline model with only 12% of the original parameters.

Shizhan Zhu, Cheng Li, Chen Change Loy et al.

Learning to simultaneously handle face alignment of arbitrary views, e.g. frontal and profile views, appears to be more challenging than we thought. The difficulties lay in i) accommodating the complex appearance-shape relations exhibited in different views, and ii) encompassing the varying landmark point sets due to self-occlusion and different landmark protocols. Most existing studies approach this problem via training multiple viewpoint-specific models, and conduct head pose estimation for model selection. This solution is intuitive but the performance is highly susceptible to inaccurate head pose estimation. In this study, we address this shortcoming through learning an Ensemble of Model Recommendation Trees (EMRT), which is capable of selecting optimal model configuration without prior head pose estimation. The unified framework seamlessly handles different viewpoints and landmark protocols, and it is trained by optimising directly on landmark locations, thus yielding superior results on arbitrary-view face alignment. This is the first study that performs face alignment on the full AFLWdataset with faces of different views including profile view. State-of-the-art performances are also reported on MultiPIE and AFW datasets containing both frontaland profile-view faces.

Shuo Yang, Ping Luo, Chen Change Loy et al.

Face detection is one of the most studied topics in the computer vision community. Much of the progresses have been made by the availability of face detection benchmark datasets. We show that there is a gap between current face detection performance and the real world requirements. To facilitate future face detection research, we introduce the WIDER FACE dataset, which is 10 times larger than existing datasets. The dataset contains rich annotations, including occlusions, poses, event categories, and face bounding boxes. Faces in the proposed dataset are extremely challenging due to large variations in scale, pose and occlusion, as shown in Fig. 1. Furthermore, we show that WIDER FACE dataset is an effective training source for face detection. We benchmark several representative detection systems, providing an overview of state-of-the-art performance and propose a solution to deal with large scale variation. Finally, we discuss common failure cases that worth to be further investigated. Dataset can be downloaded at: mmlab.ie.cuhk.edu.hk/projects/WIDERFace

Zhirong Wu, Dahua Lin, Xiaoou Tang

Binary representation is desirable for its memory efficiency, computation speed and robustness. In this paper, we propose adjustable bounded rectifiers to learn binary representations for deep neural networks. While hard constraining representations across layers to be binary makes training unreasonably difficult, we softly encourage activations to diverge from real values to binary by approximating step functions. Our final representation is completely binary. We test our approach on MNIST, CIFAR10, and ILSVRC2012 dataset, and systematically study the training dynamics of the binarization process. Our approach can binarize the last layer representation without loss of performance and binarize all the layers with reasonably small degradations. The memory space that it saves may allow more sophisticated models to be deployed, thus compensating the loss. To the best of our knowledge, this is the first work to report results on current deep network architectures using complete binary middle representations. Given the learned representations, we find that the firing or inhibition of a binary neuron is usually associated with a meaningful interpretation across different classes. This suggests that the semantic structure of a neural network may be manifested through a guided binarization process.

Shuo Yang, Ping Luo, Chen Change Loy et al.

In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW. Specifically, our method achieves a high recall rate of 90.99% on the challenging FDDB benchmark, outperforming the state-of-the-art method by a large margin of 2.91%. Importantly, we consider finding faces from a new perspective through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variation, which are the main difficulty and bottleneck of most existing face detection approaches. We show that despite the use of DCN, our network can achieve practical runtime speed.

Zhanpeng Zhang, Ping Luo, Chen Change Loy et al.

Social relation defines the association, e.g, warm, friendliness, and dominance, between two or more people. Motivated by psychological studies, we investigate if such fine-grained and high-level relation traits can be characterised and quantified from face images in the wild. To address this challenging problem we propose a deep model that learns a rich face representation to capture gender, expression, head pose, and age-related attributes, and then performs pairwise-face reasoning for relation prediction. To learn from heterogeneous attribute sources, we formulate a new network architecture with a bridging layer to leverage the inherent correspondences among these datasets. It can also cope with missing target attribute labels. Extensive experiments show that our approach is effective for fine-grained social relation learning in images and videos.