The existing UAV-assisted data harvesting and dissemination schemes largely require UAVs to frequently fly between the IoTs and access points, resulting in extra energy and time costs.
However, these two types of methods can result in accuracy loss due to discarded gradients and have limited enhancement on the throughput of model synchronization, respectively.
Existing methods are limited by the inconsistent point densities of different parts in the point cloud.
Ranked #4 on Semantic Segmentation on S3DIS
However, most of the existing SC works only transmit analog information on the AWGN channel and cannot be directly used for digital channels.
To this end, we propose a sparse state based MARL (S2RL) framework, which utilizes a sparse attention mechanism to discard irrelevant information in local observations.
The feature generated by the mobile device is transmitted through the wireless channel to the edge server.
Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans.
To handle this problem, we propose a hybrid supervision learning framework for this kind of high resolution images with sufficient image-level coarse annotations and a few pixel-level fine labels.
Specifically, Shapley Value and its desired properties are leveraged in deep MARL to credit any combinations of agents, which grants us the capability to estimate the individual credit for each agent.
Considering the problem of joint source-channel coding (JSCC) for multi-user transmission of images over noisy channels, an autoencoder-based novel deep joint source-channel coding scheme is proposed in this paper.
no code implementations • 9 Oct 2019 • Hong Yu, Xiaofan Zhang, Lingjun Song, Liren Jiang, Xiaodi Huang, Wen Chen, Chenbin Zhang, Jiahui Li, Jiji Yang, Zhiqiang Hu, Qi Duan, Wanyuan Chen, Xianglei He, Jinshuang Fan, Weihai Jiang, Li Zhang, Chengmin Qiu, Minmin Gu, Weiwei Sun, Yangqiong Zhang, Guangyin Peng, Weiwei Shen, Guohui Fu
Gastric cancer is one of the most common cancers, which ranks third among the leading causes of cancer death.
Different from conventional VPR settings where the query images and gallery images come from the same domain, we propose a more common but challenging setup where the query images are collected under a new unseen condition.
Nuclear segmentation is important and frequently demanded for pathology image analysis, yet is also challenging due to nuclear crowdedness and possible occlusion.
Our framework achieves accurate signet ring cell detection and can be readily applied in the clinical trails.