Time Efficient Training of Progressive Generative Adversarial Network using Depthwise Separable Convolution and Super Resolution Generative Adversarial Network
Generative Adversarial Networks have been employed successfully to generate high-resolution augmented images of size 1024^2. Although the augmented images generated are unprecedented, the training time of the model is exceptionally high. Conventional GAN requires training of both Discriminator as well as the Generator. In Progressive GAN, which is the current state-of-the-art GAN for image augmentation, instead of training the GAN all at once, a new concept of progressing growing of Discriminator and Generator simultaneously, was proposed. Although the lower stages such as 4x4 and 8x8 train rather quickly, the later stages consume a tremendous amount of time which could take days to finish the model training. In our paper, we propose a novel pipeline that combines Progressive GAN with slight modifications and Super Resolution GAN. Super Resolution GAN up samples low-resolution images to high-resolution images which can prove to be a useful resource to reduce the training time exponentially.
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
University of Chinese Academy of Sciences（中国科学院大学）；Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；Guangdong General Hospital, Guangdong Academy of Medical Sciences（广东省医学科学院广东省人民医院）；Henan Provincial People’s Hospital（河南省人民医院）；Nanchang University（南昌大学）
Towards Lightweight Hyperspectral Image Super-Resolution with Depthwise Separable Dilated Convolutional Network
Department of Computer Science, Aalto University, Finland（艾尔沃斯大学计算机科学系）；School of Electrical and Electronic Engineering, University of Sheffield, United Kingdom（谢菲尔德大学电子与电气工程学院）
Selective Depthwise Separable Convolution for Lightweight Joint Source-Channel Coding in Wireless Image Transmission
Singapore University of Technology and Design（新加坡科技设计大学）；National Mobile Communications Research Laboratory（国家移动通信研究中心）；Southeast University（东南大学）；School of Electronic and Optical Engineering（电子与光学工程学院）
Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）
Canizaro Livingston Gulf States Center for Environmental Informatics；University of New Orleans（新奥尔良大学）；Graz University of Technology（格拉茨技术大学）；US Army Corps of Engineers, Engineer Research and Development Center（美国陆军工程兵团，工程研究与发展中心）
Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation
Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局资讯通信研究院）；National University of Singapore（新加坡国立大学）；Singapore General Hospital（新加坡中央医院）；Duke-NUS Medical School Singapore（新加坡杜克-新加坡国立大学医学院）
DepthNet: Real-Time LiDAR Point Cloud Depth Completion for Autonomous Vehicles
自动驾驶汽车在很大程度上依赖于摄像头和激光雷达等传感器，这些传感器为感知、规划和控制任务提供有关周围环境的实时信息。通常，由于扫描线的数量有限，LiDAR只能提供稀疏的点云。通过采用深度完成，可以通过为每个相机像素分配对应的深度值来生成密集深度图。然而，现有的深度完成卷积神经网络非常复杂，需要高端GPU进行处理，因此它们不适用于实时自动驾驶。针对LiDAR点云深度补全任务，提出了一种轻量级网络。尽管参数数量减少了96.2%，但它仍然达到了与最先进网络相当的性能（MAE提高了9.3%，但RMSE降低了3.9%）。对于实时嵌入式平台，深度可分离技术应用于卷积和反卷积操作，参数的数量进一步减少了7.3倍，RMSE和MAE性能只有很小的百分比增加。此外，在基于PYNQ的FPGA平台上开发了用于深度完成的片上系统架构，该架构以每秒11.1帧的速度实现了对HDL-64 E LiDAR的实时处理。
