Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. Different from previous perspectives that focus on improving the classifiers to detect the adversarial examples, this work focuses on...
This dissertation is separated into two parts according to the two major distinct research projects. In Part I, the full account of synthetic studies toward C10-functionalized lycopodium alkaloids is described. In Part II, the detailed discussion on the exploration of the Pummerer cyclization methodology and its application to the total...
The first total syntheses of triptobenzene T, vitexifolin C, 4-epi-triptobenzene L, triptobenzene L, and nepetaefolin F have been accomplished through an enantioselective, common intermediate approach and have enabled the confirmation and/or establishment of the absolute stereochemistry of each natural product synthesized. Application of three new and/or underutilized Pummerer reaction pathways...
Two viable pathways (vinyl sulfide and acyl oxonium ion) for the Pummerer cyclization have been unraveled that expand the reaction scope and capabilities. Use of Bronsted-enhanced Lewis acidity was key to realization of the vinyl sulfide pathway, whereas selective complexation of the sulfur lone pair facilitated the unprecedented acyl oxonium...
As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
Labeling videos is costly, time-consuming and tedious. These costs can escalate in applications such as medical diagnosis or autonomous driving where we need domain expertise for annotation. Few-shot action recognition aims to solve this problem by annotation-efficient learning mechanisms.
This thesis presents MetaUVFS as the first Unsupervised Meta-learning algorithm for...
Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
This thesis consists of two major components. The first part is concerned with video object instance segmentation (VOS), which is the task of assigning per-pixel labels perframe of a video sequence to indicate foreground object instance membership, given the first frame ground truth mask. VOS has myriad applications, from video...