Jackson Childers (poppyjaguar72)

To make the network more robust to unanticipated noise perturbations, we use PGD to search for noise patterns that can trigger the network to give over-confident mistakes. By evaluating on two different benchmark datasets containing consensus annotations from three radiologists, we show that the proposed techniques can improve the detection performance on real CT data. To understand the limitations of both the conventional networks and the proposed augmented networks, we also perform stress-tests on the false positive reduction networks by feeding different types of artificially produced patches. We show that the augmented networks are more robust to both under-represented nodules as well as resistant to noise perturbations.The quantification of 3D shape aesthetics has so far focused on specific shape features and manually defined criteria such as the curvature and the rule of thirds respectively. In this paper, we build a model of 3D shape aesthetics directly from human aesthetics preference data and show it to be well aligned with human perception of aesthetics. To build this model, we first crowdsource a large number of human aesthetics preferences by showing shapes in pairs in an online study and then use the same to build a 3D shape multi-view based deep neural network architecture to allow us learn a measure of 3D shape aesthetics. In comparison to previous approaches, we do not use any pre-defined notions of aesthetics to build our model. Our algorithmically computed measure of shape aesthetics is beneficial to a range of applications in graphics such as search, visualization and scene composition.We developed a minimum-cost circulation framework for solving the global data association problem, which plays a key role in the tracking-by-detection paradigm of multi-object tracking. The problem was extensively studied under the minimum-cost flow framework, which is theoretically attractive as being flexible and globally solvable. However, the high computational burden has been a long-standing obstacle to its wide adoption in practice. While enjoying the same theoretical advantages and maintaining the same optimal solution as the minimum-cost flow framework, our new framework has a better theoretical complexity bound and leads to orders of practical efficiency improvement. Exploring the specialty that an overwhelming majority of the vertices are with unit capacity, we designed an implementation of the framework and proved it has the best theoretical complexity so far. We evaluated our method with 40 experiments on five MOT benchmark data sets. Our method was always the most efficient and averagely 53 to 1,192 times faster than the three state-of-the-art methods. When our method served as a sub-module for global data association methods using higher-order constraints, similar efficiency improvement was attained. We further illustrated through several case studies how the improved computational efficiency enables more sophisticated tracking models and yields better tracking accuracy.Domain adaptation, which transfers the knowledge from label-rich source domain to unlabeled target domains, is a challenging task in machine learning. The prior domain adaptation methods focus on pairwise adaptation assumption with a single source and a single target domain, while little work concerns the scenario of one source domain and multiple target domains. Applying pairwise adaptation methods to this setting may be suboptimal, as they fail to consider the semantic association among multiple target domains. In this work we propose a deep semantic information propagation approach in the novel context of multiple unlabeled target domains and one labeled source domain. Our model aims to learn a unified subspace common for all domains with a heterogeneous graph attention network, where the transductive ability of the graph attention network can conduct semantic propagation of the related samples among multiple domains.