In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expensive key-point labels, part annotations, and additional attributes including vehicle make, model, and color. Given the large number of vehicle re-id datasets with various levels of annotations, strongly-supervised methods are unable to scale across different domains. In this paper, we present Self-supervised Attention for Vehicle Re-identification (SAVER), a novel approach to effectively learn vehicle-specific discriminative features. Through extensive experimentation, we show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets.
In this paper, we propose a novel optimization criterion that leverages features of the skew normal distribution to better model the problem of personalized recommendation. Specifically, the developed criterion borrows the concept and the flexibility of the skew normal distribution, based on which three hyperparameters are attached to the optimization criterion. Furthermore, from a theoretical point of view, we not only establish the relation between the maximization of the proposed criterion and the shape parameter in the skew normal distribution, but also provide the analogies and asymptotic analysis of the proposed criterion to maximization of the area under the ROC curve. Experimental results conducted on a range of large-scale real-world datasets show that our model significantly outperforms the state of the art and yields consistently best performance on all tested datasets.
Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this article, we propose a new vector neural architecture called the Arbitrary BIlinear Product NN (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convolution, 7-D vector product, skew circular convolution, reversed-time circular convolution, or other new products that are not seen in the previous work. As a proof-of-concept, we apply our proposed network to multispectral image denoising and singing voice separation. Experimental results show that ABIPNN obtains substantial improvements when compared to conventional NNs, suggesting that associations are learned during training.
Spatiotemporal super-resolution (SR) aims to upscale both the spatial and temporal dimensions of input videos, and produces videos with higher frame resolutions and rates. It involves two essential sub-tasks: spatial SR and temporal SR. We design a two-stream network for spatiotemporal SR in this work. One stream contains a temporal SR module followed by a spatial SR module, while the other stream has the same two modules in the reverse order. Based on the interchangeability of performing the two sub-tasks, the two network streams are supposed to produce consistent spatiotemporal SR results. Thus, we present a cross-stream consistency to enforce the similarity between the outputs of the two streams. In this way, the training of the two streams is correlated, which allows the two SR modules to share their supervisory signals and improve each other. In addition, the proposed cross-stream consistency does not consume labeled training data and can guide network training in an unsupervised manner. We leverage this property to carry out semi-supervised spatiotemporal SR. It turns out that our method makes the most of training data, and can derive an effective model with few high-resolution and high-frame-rate videos, achieving the state-of-the-art performance.
Mobile/multi-access edge computing (MEC) is therefore developed to support the upcoming AI-aware mobile services, which require low latency and intensive computation resources at the edge of the network. One of the most challenging issues in MEC is service provision with mobility consideration. It has been known that the offloading and migration decision need to be jointly handled to maximize the utility of networks within the latency constraints, which is challenging when users are in mobility. In this paper, we propose Mobility-Aware Deep Reinforcement Learning (M-DRL) framework for mobile service provision problems in the MEC system. M-DRL is composed of two parts: DRL specialized in supporting multiple users joint training, and glimpse, a seq2seq model customized for mobility prediction to predict a sequence of locations just like a "glimpse" of future. Through integrating the proposed DRL and glimpse mobility prediction model, the proposed M-DRL framework is optimized to handle the service provision problem in MEC with acceptable computation complexity and near optimal performance.
Mobile Edge Computing (MEC) is a promising technique in the 5G Era to improve the Quality of Experience (QoE) for online video streaming due to its ability to reduce the backhaul transmission by caching certain content. However, it still takes effort to address the user association and video quality selection problem under the limited resource of MEC to fully support the low-latency demand for live video streaming. We found the optimization problem to be a non-linear integer programming, which is impossible to obtain a globally optimal solution under polynomial time. In this paper, we first reformulate this problem as a Markov Decision Process (MDP) and develop a Deep Deterministic Policy Gradient (DDPG) based algorithm exploiting the supply-demand interpretation of the Lagrange dual problem. Simulation results show that our proposed approach achieves significant QoE improvement especially in the low wireless resource and high user number scenario compared to other baselines.
The live video streaming services have been suffered from the limited backhaul capacity of the cellular core network and occasional congestions due to the cloud-based architecture. Mobile Edge Computing (MEC) brings the services from the centralized cloud to nearby network edge to improve the Quality of Experience (QoE) of cloud services, such as live video streaming services. Nevertheless, the resource at edge devices is still limited and should be allocated economically efficiently. In this paper, we propose Edge Combinatorial Clock Auction (ECCA) and Combinatorial Clock Auction in Stream (CCAS), two auction frameworks to improve the QoE of live video streaming services in the Edge-enabled cellular system. The edge system is the auctioneer who decides the backhaul capacity and caching space allocation and streamers are the bidders who request for the backhaul capacity and caching space to improve the video quality their audiences can watch. There are two key subproblems: the caching space value evaluations and allocations. We show that both problems can be solved by the proposed dynamic programming algorithms. The truth-telling property is guaranteed in both ECCA and CCAS. The simulation results show that the overall system utility can be significantly improved through the proposed system.
Recent advances in deep convolutional neural networks (DCNNs) and generative adversarial networks (GANs) have significantly improved the performance of single image blind deblurring algorithms. However, most of the existing algorithms require paired training data. In this paper, we present an unsupervised method for single-image deblurring without paired training images. We introduce a disentangled framework to split the content and blur features of a blurred image, which yields improved deblurring performance. To handle the unpaired training data, a blurring branch and the cycle-consistency loss are added to guarantee that the content structures of the restored results match the original images. We also add a perceptual loss to further mitigate the artifacts. For natural image deblurring, we introduce a color loss to reduce color distortions in outputs. Extensive experiments on both domain-specific and natural image deblurring show the proposed method achieves competitive results compared to recent state-of-the-art deblurring approaches.
The network attack such as Distributed Denial-of-Service (DDoS) attack could be critical to latency-critical systems such as Mobile Edge Computing (MEC) as such attacks significantly increase the response delay of the victim service. Intrusion prevention system (IPS) is a promising solution to defend against such attacks, but there will be a trade-off between IPS deployment and application resource reservation as the deployment of IPS will reduce the number of computation resources for MEC applications. In this paper, we proposed a game-theoretic framework to study the joint computation resource allocation and IPS deployment in the MEC architecture. We study the pricing strategy of the MEC platform operator and purchase strategy of the application service provider, given the expected attack strength and end user demands. The best responses of both MPO and ASPs are derived theoretically to identify the Stackelberg equilibrium. The simulation results confirm that the proposed solutions significantly increase the social welfare of the system.
Intermittent computing enables battery-less systems to support complex tasks such as face recognition through energy harvesting, but without an installed battery. Nevertheless, the latency may not be satisfied due to the limited computing power. Integrating mobile edge computing (MEC) with intermittent computing would be the desired solution to reduce latency and increase computation efficiency. In this work, we investigate the joint optimization problem of bandwidth allocation and the computation offloading with multiple battery-less intermittent devices in a wireless MEC network. We provide a comprehensive analysis of the expected offloading efficiency, and then propose Greedy Adaptive Balanced Allocation and Offloading (GABAO) algorithm considering the energy arrival distributions, remaining task load, and available computing/communication resources. Simulation results show that the proposed system can significantly reduce the latency in a multi-user MEC network with battery-less devices.