We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density Map Estimator (DME) then generates high-quality density maps. With the attention-aware training scheme and multiscale deformable convolutional scheme, the proposed AD-CrowdNet achieves the capability of being more effective to capture the crowd features and more resistant to various noises. We have evaluated our method on four popular crowd counting datasets (ShanghaiTech, UCF CC 50, WorldEXPO'10, and UCSD) and an extra vehicle counting dataset TRANCOS, and our approach beats existing stateof-the-art approaches on all of these datasets.

No abstract

Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose an innovative additional purification step for further weight reduction without accuracy loss; and (iii) develop effective heuristic search method enhanced by experience-based guided search, replacing the prior deep reinforcement learning technique which has underlying incompatibility with the target pruning problem. Extensive experiments on CIFAR-10 and ImageNet datasets demonstrate that AutoCompress is the key to achieve ultra-high pruning rates on the number of weights and FLOPs that cannot be achieved before. As an example, AutoCompress outperforms the prior work on automatic model compression by up to 33× in pruning rate (120× reduction in the actual parameter count) under the same accuracy. Significant inference speedup has been observed from the AutoCompress framework on actual measurements on smartphone. We release models of this work at anonymous link: http://bit.ly/2VZ63dS.

Deep reinforcement learning (RL) has become one of the most popular topics in artificial intelligence research. It has been widely used in various fields, such as end-to-end control, robotic control, recommendation systems, and natural language dialogue systems. In this survey, we systematically categorize the deep RL algorithms and applications, and provide a detailed review over existing deep RL algorithms by dividing them into modelbased methods, model-free methods, and advanced RL methods. We thoroughly analyze the advances including exploration, inverse RL, and transfer RL. Finally, we outline the current representative applications, and analyze four open problems for future research.

No abstract

Due to the huge popularity of wireless networks, future designs will not only consider the provided capacity, but also the induced exposure, the corresponding power consumption, and the economic cost. As these requirements are contradictory, it is not straightforward to design optimal wireless networks. Those contradicting demands have to satisfy certain requirements in practice. In this paper, a combination of two algorithms, a genetic algorithm and a quasi-particle swarm optimization, is developed, yielding a novel hybrid algorithm that generates further optimizations of indoor wireless network planning solutions, which is named hybrid indoor genetic optimization algorithm. The algorithm is compared with a heuristic network planner and composite differential evolution algorithm for three scenarios and two different environments. Results show that our hybrid-algorithm is effective for optimization of wireless networks which satisfy four demands: maximum coverage for a user-defined capacity, minimum power consumption, minimal cost, and minimal human exposure

No abstract

No abstract