Due to memory constraints on current hardware, most convolution neural networks (CNN) are trained on sub-megapixel images. For example, most popular datasets in computer vision contain images much less than a megapixel in size (0.09MP for ImageNet and 0.001MP for CIFAR-10). In some domains such as medical imaging, multi-megapixel images are needed to identify the presence of disease accurately. We propose a novel method to directly train convolutional neural networks using any input image size end-to-end. This method exploits the locality of most operations in modern convolutional neural networks by performing the forward and backward pass on smaller tiles of the image. In this work, we show a proof of concept using images of up to 66-megapixels (8192x8192), saving approximately 50GB of memory per image. Using two public challenge datasets, we demonstrate that CNNs can learn to extract relevant information from these large images and benefit from increasing resolution. We improved the area under the receiver-operating characteristic curve from 0.580 (4MP) to 0.706 (66MP) for metastasis detection in breast cancer (CAMELYON17). We also obtained a Spearman correlation metric approaching state-of-the-art performance on the TUPAC16 dataset, from 0.485 (1MP) to 0.570 (16MP). Code to reproduce a subset of the experiments is available at https://github.com/DIAGNijmegen/StreamingCNN.
Online Streaming Video Super-Resolution with Convolutional Look-Up Table
Zhejiang University（浙江大学）；Tongji University（同济大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Jiao Tong University（上海交通大学）；Microsoft Research Asia（微软亚洲研究院）
An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D DCT Perceptual Encoding for High Dynamic Range Light Fields
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
Inha University（仁荷大学）
流图像中的目标检测是不同的基于检测的应用中的主要步骤，诸如对象跟踪、动作识别、机器人导航和视觉监视应用。在大多数情况下，图像质量是有噪声和偏见的，因此，数据分布受到干扰和不平衡。大多数目标检测方法，例如更快的基于区域的卷积神经网络（Faster RCNN），具有300 x 300输入的Single Shot Multibox Detector（SSD 300）和You Only Look Once version 2（YOLOv2），依赖于简单的采样，而不考虑真实世界变化环境下的失真和噪声，尽管对象标记很差。在本文中，我们提出了一种增量主动半监督学习（IASSL）技术的不可见目标检测。它结合了基于批的主动学习（AL）和基于bin的半监督学习（SSL），以利用AL的探索和SSL的开发能力的优点。采用协同抽样的方法来衡量AL的不确定性和多样性以及SSL的置信度。基于批次的AL使我们能够以低成本选择更具信息性，置信度和代表性的样品。基于bin的SSL将流式图像样本划分为若干bin，每个bin将卷积神经网络（CNN）深度学习的判别知识重复传输到下一个bin，直到达到性能标准。IASSL可以克服噪声和偏见的标签在未知的，杂乱的数据分布。与Faster RCNN、SSD300和YOLOv2等最先进的技术相比，我们获得了卓越的性能。
On-Device Inference versus Wireless Streaming: Energy-Efficient Multi-Modal Deep Learning for Wearable Cardiovascular Patches
CTO System Innovation, NXP Semiconductors Germany GmbH（NXP半导体德国系统创新部）；Advanced Chip Engineering, NXP Semiconductors（NXP半导体先进芯片工程部）；Business Line Secure Connected Edge, NXP Semiconductors（NXP半导体安全连接边缘业务线）；Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology（汉堡技术大学医学技术与智能系统研究所）；Department of Informatics, Hamburg University of Applied Sciences（汉堡应用科学大学信息学院）
Multi-pooled Inception features for no-reference image quality assessment
图像质量评估（IQA）是从自动视频流到显示技术的广泛应用的重要组成部分。此外，图像质量的测量需要对图像内容和特征进行平衡的调查。我们提出的方法通过将全局平均池（GAP）层附加到ImageNet数据库预训练卷积神经网络（CNN）的多个Inception模块来提取视觉特征。与以前的方法相比，我们不从输入图像中获取补丁。相反，输入图像被视为一个整体，并通过预训练的CNN主体来提取分辨率无关的多级深度特征。因此，我们的方法可以很容易地推广到任何输入图像大小和预训练的CNN。因此，我们提出了一个详细的参数研究方面的CNN基础架构和不同的深度功能的有效性。我们证明，我们最好的建议-称为MultiGAP-NRIQA -是能够提供国家的最先进的三个基准IQA数据库的结果。此外，这些结果也在使用LIVE In the Wild Image Quality Challenge数据库的交叉数据库测试中得到了证实。
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
Intel IAGS SSP（英特尔IAGS SSP）；Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学武汉光电国家研究中心）；Huazhong University of Science and Technology（华中科技大学）
FPGA Implementations of 3D-SIMD Processor Architecture for Deep Neural Networks Using Relative Indexed Compressed Sparse Filter Encoding Format and Stacked Filters Stationary Flow
Malware Detection in Docker Containers: An Image is Worth a Thousand Logs
K3Y Ltd（K3Y有限公司）；International Hellenic University（国际希腊大学）；Kingston University（金斯顿大学）；University of Peloponnese（伯罗奔尼撒大学）；Aristotle University of Thessaloniki（亚里士多德大学）；Hellenic Mediterranean University（希腊地中海大学）；University of Western Macedonia（西马其顿大学）
