Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training datasets. This presents a fundamental problem for applications with limited, expensive, or private data (i.e. small data), such as human pose and behavior estimation/tracking which could be highly personalized. In this paper, we present a semi-supervised data augmentation approach that can synthesize large scale labeled training datasets using 3D graphical engines based on a physically-valid low dimensional pose descriptor. To evaluate the performance of our synthesized datasets in training deep learning-based models, we generated a large synthetic human pose dataset, called ScanAva using 3D scans of only 7 individuals based on our proposed augmentation approach. A state-of-the-art human pose estimation deep learning model then was trained from scratch using our ScanAva dataset and could achieve the pose estimation accuracy of 91.2% at PCK0.5 criteria after applying an efficient domain adaptation on the synthetic images, in which its pose estimation accuracy was comparable to the same model trained on large scale pose data from real humans such as MPII dataset and much higher than the model trained on other synthetic human dataset such as SURREAL.
Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture
Sichuan University（四川大学）
自动数据增强是近年来研究的热点，其目的是自动制定工程增强策略。许多以前的自动增强方法利用密度匹配策略，通过评估测试时增强性能方面的政策。在本文中，我们从理论上和经验证明之间的不一致性的训练和验证集的小规模医学图像数据集，称为域内采样偏差。接下来，我们证明了域内采样偏差可能导致密度匹配的效率低下。针对这一问题，提出了一种改进的增广搜索策略--增广密度匹配（Augmented Density Matching），该策略从先验分布中随机抽取策略进行训练。此外，通过统一数据增强和神经结构的搜索，提出了一种高效的自动机器学习（AutoML）算法。实验结果表明，所提出的方法优于最先进的方法MedMNIST，一个开创性的基准设计的AutoML在医学图像分析。
Ctrl-A: Control-Driven Machine Learning using Adaptive Online Data Augmentation
Danish Fundamental Metrology (DFM)（丹麦基础计量院）；National Physical Laboratory (NPL)（国家物理实验室）；TÜV SÜD；Royal Surrey NHS Foundation Trust（皇家萨里国家健康服务基金会信托）；Istituto Nazionale di Ricerca Metrologica (INRiM)（意大利国家计量研究院）
Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?
Australian National University（澳大利亚国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Monash University（蒙纳士大学）；University of New South Wales（新南威尔士大学）；Shanghai Jiao Tong University（上海交通大学）
