arXiv subjects

Xing Wei

Publications and source records attributed to Xing Wei.

At least 91 records · Page 5Linked to original sources

arXiv2021

Anomaly Detection via Self-organizing Map

Anomaly detection plays a key role in industrial manufacturing for product quality control. Traditional methods for anomaly detection are rule-based with limited generalization ability. Recent methods based on supervised deep learning are more powerful but require large-scale annotated datasets for training. In practice, abnormal products are rare thus it is very difficult to train a deep model in a fully supervised way. In this paper, we propose a novel unsupervised anomaly detection approach based on Self-organizing Map (SOM). Our method, Self-organizing Map for Anomaly Detection (SOMAD) maintains normal characteristics by using topological memory based on multi-scale features. SOMAD achieves state-of the-art performance on unsupervised anomaly detection and localization on the MVTec dataset.

cs.CV↗

arXiv2021

Direct Measure Matching for Crowd Counting

Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. First, crowd counting is formulated as a measure matching problem. Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching. Third, we propose a self-supervised mechanism by devising a Sinkhorn scale consistency loss to resist scale changes. Finally, an efficient optimization method is provided to minimize the overall loss function. Extensive experiments on four challenging crowd counting datasets namely ShanghaiTech, UCF-QNRF, JHU++, and NWPU have validated the proposed method.

cs.CV↗

arXiv2021

Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration

In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation. Most existing MOT methods track multiple objects using a singular RGB camera, which are prone to camera field-of-view and suffer tracking failures in complex scenarios due to background clutters and poor light conditions. To meet these challenges, we propose a MultiModality PAnoramic multi-object Tracking framework (MMPAT), which takes both 2D panorama images and 3D point clouds as input and then infers target trajectories using the multimodality data. The proposed method contains four major modules, a panorama image detection module, a multimodality data fusion module, a data association module and a trajectory inference model. We evaluate the proposed method on the JRDB dataset, where the MMPAT achieves the top performance in both the detection and tracking tasks and significantly outperforms state-of-the-art methods by a large margin (15.7 and 8.5 improvement in terms of AP and MOTA, respectively).

cs.CV↗

arXiv2021

Spatial Privacy-aware VR streaming

Proactive tile-based virtual reality (VR) video streaming employs the current tracking data of a user to predict future requested tiles, then renders and delivers the predicted tiles before playback. Very recently, privacy protection in proactive VR video streaming starts to raise concerns. However, existing privacy protection may fail even with privacy-preserve federated learning. This is because when the future requested tiles can be predicted accurately, the user-behavior-related data can still be recovered from the predicted tiles. In this paper, we consider how to protect privacy even with accurate predictors and investigate the impact of privacy requirement on the quality of experience (QoE). To this end, we first add extra \textit{camouflaged} tile requests to the real tile requests and model the privacy requirement as the \textit{spatial degree of privacy} (sDoP). By ensuring sDoP, the real tile requests can be hidden and privacy can be protected. Then, we jointly optimize the durations for prediction, computing, and transmitting, aimed at maximizing the privacy-aware QoE given arbitrary predictor and configured resources. From the obtained optimal closed-form solution, we find that the impacts of sDoP on the QoE are two sides of the same coin. On the one side the increase of sDoP improves the capability of communication and computing hence improves QoE. On the other side it degrades the prediction performance hence degrades the QoE. The overall impact depends on which factor dominates the QoE. Simulation with two predictors on a real dataset verifies the analysis and shows that the overall impact of sDoP is to improve the QoE.

cs.MM↗

arXiv2021

Privacy-aware VR streaming

Proactive tile-based virtual reality (VR) video streaming employs the current tracking data of a user to predict future requested tiles, then renders and delivers the predicted tiles to be requested before playback. The quality of experience (QoE) depends on the overall performance of prediction, computing (i.e., rendering) and communication. All prior works neglect that users may have privacy requirement, i.e., not all the current tracking data are allowed to be uploaded. In this paper, we investigate the privacy-aware VR streaming. We first establish a dataset that collects the privacy requirement of 66 users among 18 panoramic videos. The dataset shows that the privacy requirements of 360$^{\circ}$ videos are heterogeneous. Only 41\% of the total watched videos have no privacy requirement. Based on these findings, we formulate the privacy requirement as the \textit{degree of privacy} (DoP), and investigate the impact of DoP on the proactive VR streaming. First, we find that with DoP, the length of the observation window and prediction window of a tile predictor should be variable. Then, we jointly optimize the durations for computing and transmitting the selected tiles as well as the computing and communication capability, aimed at maximizing the QoE given arbitrary predictor and configured resources. From the obtained optimal closed-form solution, we find a resource-saturated region where DoP has no impact on the QoE and a resource-unsaturated region where the two-fold impacts of DoP are contradictory. On the one hand, the increase of DoP will degrade the prediction performance and thus degrade the QoE. On the other hand, the increase of DoP will improve the capability of computing and communication and thus improve the QoE. Simulation results using two predictors and a real dataset validate the analysis and demonstrate the overall impact of DoP on the QoE.

cs.MM↗

arXiv2021

Self-Distribution Binary Neural Networks

In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for deep neural networks, while in BNNs, the features only differ in signs. Prior work introduces scaling factors into binary weights and activations to reduce the quantization error and effectively improves the classification accuracy of BNNs. However, the scaling factors not only increase the computational complexity of networks, but also make no sense to the signs of binary features. To this end, Self-Distribution Binary Neural Network (SD-BNN) is proposed. Firstly, we utilize Activation Self Distribution (ASD) to adaptively adjust the sign distribution of activations, thereby improve the sign differences of the outputs of the convolution. Secondly, we adjust the sign distribution of weights through Weight Self Distribution (WSD) and then fine-tune the sign distribution of the outputs of the convolution. Extensive experiments on CIFAR-10 and ImageNet datasets with various network structures show that the proposed SD-BNN consistently outperforms the state-of-the-art (SOTA) BNNs (e.g., achieves 92.5% on CIFAR-10 and 66.5% on ImageNet with ResNet-18) with less computation cost. Code is available at https://github.com/ pingxue-hfut/SD-BNN.

cs.CV↗

arXiv2021

Enhancement of wave transmissions in multiple radiative and convective zones

In this paper, we study wave transmission in a rotating fluid with multiple alternating convectively stable and unstable layers. We have discussed wave transmissions in two different circumstances: cases where the wave is propagative in each layer and cases where wave tunneling occurs. We find that efficient wave transmission can be achieved by `resonant propagation' or `resonant tunneling', even when stable layers are strongly stratified, and we call this phenomenon `enhanced wave transmission'. Enhanced wave transmission only occurs when the total number of layers is odd (embedding stable layers are alternatingly embedded within clamping convective layers, or vise versa). For wave propagation, the occurrence of enhanced wave transmission requires that clamping layers have similar properties, the thickness of each clamping layer is close to a multiple of the half wavelength of the corresponding propagative wave, and the total thickness of embedded layers is close to a multiple of the half wavelength of the corresponding propagating wave (resonant propagation). For wave tunneling, we have considered two cases: tunneling of gravity waves and tunneling of inertial waves. In both cases, efficient tunneling requires that clamping layers have similar properties, the thickness of each embedded layer is much smaller than the corresponding e-folding decay distance, and the thickness of each clamping layer is close to a multiple-and-a-half of half wavelength (resonant tunneling).

physics.flu-dyn↗

arXiv2021

Inertial and gravity wave transmissions near radiative-convective boundaries

In this paper, we study the inertial and gravity wave transmissions near the radiative-convective boundaries in the {\it f}-plane. Two configurations have been considered: waves propagate from the convective layer to the radiative stratified stable layer, or In this paper, we study inertial and gravity wave transmissions near radiative-convective boundaries on the {\it f}-plane. Two configurations have been considered: waves propagate from the convective layer to the radiative stratified stable layer, or the other way around. It has been found that waves prefer to survive at low latitudes when the stable layer is strongly stratified ($N^2/(2Ω)^2>1$). When the stable layer is weakly stratified ($N^2/(2Ω)^2<1$), however, waves can survive at any latitude if the meridional wavenumber is large. Then we have discussed transmission ratios for two buoyancy frequency structures: the uniform stratification, and the continuously varying stratification. For the uniform stratification, we have found that the transmission is efficient when the rotation is rapid, or when the wave is near the critical colatitude. For the continuously varying stratification, we have discussed the transmission ratio when the square of buoyancy frequency is an algebraic function $N^2\propto z^ν (ν>0)$. We have found that the transmission can be efficient when the rotation is rapid, or when the wave is near the critical colatitude, or when the thickness of the stratification layer is far greater than the horizontal wave length. The transmission ratio does not depend on the configurations (radiative layer sits above convective layer, or vice versa; wave propagates outward or inward), but only on characteristics of the wave (frequency and wavenumber) and the fluid (degree of stratification).

physics.flu-dyn↗

arXiv2021

Duration-Squeezing-Aware Communication and Computing for Proactive VR

Proactive tile-based virtual reality video streaming computes and delivers the predicted tiles to be requested before playback. All existing works overlook the important fact that computing and communication (CC) tasks for a segment may squeeze the time for the tasks for the next segment, which will cause less and less available time for the latter segments. In this paper, we jointly optimize the durations for CC tasks to maximize the completion rate of CC tasks under the task duration-squeezing-aware constraint. To ensure the latter segments remain enough time for the tasks, the CC tasks for a segment are not allowed to squeeze the time for computing and delivering the subsequent segment. We find the closed-form optimal solution, from which we find a minimum-resource-limited, an unconditional and a conditional resource-tradeoff regions, which are determined by the total time for proactive CC tasks and the playback duration of a segment. Owing to the duration-squeezing-prohibited constraints, the increase of the configured resources may not be always useful for improving the completion rate of CC tasks. Numerical results validate the impact of the duration-squeezing-prohibited constraints and illustrate the three regions.

cs.MM↗

arXiv2020

Beyond Universal Person Re-ID Attack

Deep learning-based person re-identification (Re-ID) has made great progress and achieved high performance recently. In this paper, we make the first attempt to examine the vulnerability of current person Re-ID models against a dangerous attack method, \ie, the universal adversarial perturbation (UAP) attack, which has been shown to fool classification models with a little overhead. We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack. Firstly, we adopt a list-wise attack objective function to disrupt the similarity ranking list directly. Secondly, we propose a model-insensitive mechanism for cross-model attack. Extensive experiments show that the proposed attack approach achieves high attack performance and outperforms other state of the arts by large margin in cross-model scenario. The results also demonstrate the vulnerability of current Re-ID models to MUAP and further suggest the need of designing more robust Re-ID models.

cs.CV↗

arXiv2020

UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration

To apply deep CNNs to mobile terminals and portable devices, many scholars have recently worked on the compressing and accelerating deep convolutional neural networks. Based on this, we propose a novel uniform channel pruning (UCP) method to prune deep CNN, and the modified squeeze-and-excitation blocks (MSEB) is used to measure the importance of the channels in the convolutional layers. The unimportant channels, including convolutional kernels related to them, are pruned directly, which greatly reduces the storage cost and the number of calculations. There are two types of residual blocks in ResNet. For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks. For ResNet with basic residual blocks, we propose an approach to consistently prune all residual blocks in the same stage to ensure that the compact network structure is dimensionally correct. Considering that the network loses considerable information after pruning and that the larger the pruning amplitude is, the more information that will be lost, we do not choose fine-tuning but retrain from scratch to restore the accuracy of the network after pruning. Finally, we verified our method on CIFAR-10, CIFAR-100 and ILSVRC-2012 for image classification. The results indicate that the performance of the compact network after retraining from scratch, when the pruning rate is small, is better than the original network. Even when the pruning amplitude is large, the accuracy can be maintained or decreased slightly. On the CIFAR-100, when reducing the parameters and FLOPs up to 82% and 62% respectively, the accuracy of VGG-19 even improved by 0.54% after retraining.

cs.CV↗

arXiv2020

Wave reflection and transmission at interface of convective and stably stratified regions in a rotating star or planet

We use a simplified model to study wave reflection and transmission at interface of convective region and stably stratified region (e.g. radiative zone in star or stratification layer in gaseous planet). Inertial wave in convective region and gravito-inertial wave in stably stratified region are considered. We begin with polar area and then extend to any latitude. Six cases are discussed (see Table 1), and in Case 2 both waves co-exist in both regions. Four configurations are further discussed for Case 2. The angles and energy ratios of wave reflection and transmission are calculated. It is found that wave propagation and transmission depend on the ratio of buoyancy frequency to rotational frequency. In a rapidly rotating star or planet wave propagates across interface and most of energy of incident wave is transmitted to the other region, but in a slowly rotating star or planet wave transmission is inhibited.

astro-ph.SR↗

arXiv2020

On the evolution of global ocean tides

We apply Laplace's tidal theory to the evolution of lunar and solar tides on the geologic timescale of Earth's rotation and focus on the tidal resonance. We study the global tide in the mid-ocean far away from continents. On the short timescale, a linear relationship of tidal height and Earth's rotation is obtained. On the long timescale, the tide is less than 1 metre at present but it was 5 metres in the past and will reach 8 metres in the future because of resonances of tidal wave and Earth's rotation. We conclude that the Earth-Moon orbital separation and the slowdown of Earth's rotation are faster than expected before.

astro-ph.EP↗

arXiv2020

Few-Shot Class-Incremental Learning

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets.

cs.CV↗

arXiv2020

Person Re-identification in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), visual surveillance by utilizing the UAV platform has been very attractive. Most of the research works for UAV captured visual data are mainly focused on the tasks of object detection and tracking. However, limited attention has been paid to the task of person Re-identification (ReID) which has been widely studied in ordinary surveillance cameras with fixed emplacements. In this paper, to facilitate the research of person ReID in aerial imagery, we collect a large scale airborne person ReID dataset named as Person ReID for Aerial Imagery (PRAI-1581), which consists of 39,461 images of 1581 person identities. The images of the dataset are shot by two DJI consumer UAVs flying at an altitude ranging from 20 to 60 meters above the ground, which covers most of the real UAV surveillance scenarios. In addition, we propose to utilize subspace pooling of convolution feature maps to represent the input person images. Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently. We conduct extensive experiments on the proposed dataset and the experimental results demonstrate that re-identify persons in aerial imagery is a challenging problem, where our method performs favorably against state of the arts. Our dataset can be accessed via \url{https://github.com/stormyoung/PRAI-1581}.

cs.CV↗

arXiv2019

Bayesian Loss for Crowd Count Estimation with Point Supervision

In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map estimation, which convert the sparse point annotations into a "ground truth" density map through a Gaussian kernel, and then use it as the learning target to train a density map estimator. However, such a "ground-truth" density map is imperfect due to occlusions, perspective effects, variations in object shapes, etc. On the contrary, we propose \emph{Bayesian loss}, a novel loss function which constructs a density contribution probability model from the point annotations. Instead of constraining the value at every pixel in the density map, the proposed training loss adopts a more reliable supervision on the count expectation at each annotated point. Without bells and whistles, the loss function makes substantial improvements over the baseline loss on all tested datasets. Moreover, our proposed loss function equipped with a standard backbone network, without using any external detectors or multi-scale architectures, plays favourably against the state of the arts. Our method outperforms previous best approaches by a large margin on the latest and largest UCF-QNRF dataset. The source code is available at \url{https://github.com/ZhihengCV/Baysian-Crowd-Counting}.

cs.CV↗

arXiv2019

Reinforcement Learning Based Emotional Editing Constraint Conversation Generation

In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This paper proposes a conversation content generation model that combines reinforcement learning with emotional editing constraints to generate more meaningful and customizable emotional replies. The model divides the replies into three clauses based on pre-generated keywords and uses the emotional editor to further optimize the final reply. The model combines multi-task learning with multiple indicator rewards to comprehensively optimize the quality of replies. Experiments shows that our model can not only improve the fluency of the replies, but also significantly enhance the logical relevance and emotional relevance of the replies.

cs.CL↗

arXiv2019

Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets

Frequent mine disasters cause a large number of casualties and property losses. Autonomous driving is a fundamental measure for solving this problem, and track detection is one of the key technologies for computer vision to achieve downhole automatic driving. The track detection result based on the traditional convolutional neural network (CNN) algorithm lacks the detailed and unique description of the object and relies too much on visual postprocessing technology. Therefore, this paper proposes a track detection algorithm based on a multiscale conditional generative adversarial network (CGAN). The generator is decomposed into global and local parts using a multigranularity structure in the generator network. A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator. Finally, the Monte Carlo search technique is introduced to search the intermediate state of the generator, and the result is sent to the discriminator for comparison. Compared with the existing work, our model achieved 82.43\% pixel accuracy and an average intersection-over-union (IOU) of 0.6218, and the detection of the track reached 95.01\% accuracy in the downhole roadway scene test set.

cs.CV↗