Master's thesis presentation

Jian Deng, Master’s candidate
David R. Cheriton School of Computer Science

This thesis presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework \cite{girshick2015fast} \cite{ren2015faster}. A Region Proposal Network (RPN) generates 3D proposals in a Bird's Eye View (BEV) projection of the point cloud. The second stage projects the 3D proposal bounding boxes to the image and BEV feature maps and sends the corresponding map crops to a detection header for classification and bounding-box regression.

Alexander Sachs, Master’s candidate
David R. Cheriton School of Computer Science

GitHub is an excellent democratic source of software. Unlike traditional work groups however, GitHub repositories are primarily anonymous and virtual. Traditional strategies for improving the productivity of a work group often include external consultation agencies that do in-person interviews. The resulting data from these interviews are then reviewed and their recommendations provided. In the online world however, where colleagues are often anonymous and geographically dispersed, it is often impossible to apply such approaches.

Jonathan Vi Perrie, Master’s candidate
David R. Cheriton School of Computer Science

Over the years, hit song science has been a controversial topic within music information retrieval (MIR). Researchers have debated whether an unbiased dataset can be constructed and what it means to successfully model song performance. Often classes for modelling are derived from one component of song performance, like for example, a song's peak position on some chart. 

Rahul Iyer, Master’s candidate
David R. Cheriton School of Computer Science

Social interactions in the form of discussion are an indispensable part of collaborative software development. The discussions are essential for developers to share their views and to form a strong relationship with other teammates. These discussions invoke both positive and negative emotions such as joy, love, aggression, and disgust. Additionally, developers also exhibit hidden behaviors that dictate their personality. Some developers can be supportive and open to new ideas, whereas others can be conservative. Past research has shown that the personality of the developers has a significant role in determining the success of the task they collaboratively perform.

Matthew Angus, Master’s candidate
David R. Cheriton School of Computer Science

There exists wide research surrounding the detection of out of distribution sample for image classification. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing an image to be out of distribution. 

Yingluo Xun, Master’s candidate
David R. Cheriton School of Computer Science

In reinforcement learning, entropy-regularized value function (in policy space) has attracted a lot of attention recently due to its effect on smoothing the value function, and the effect on encouraging exploration. However, there is a discrepancy between the regularized objective function and the original objective function in existing methods, which would potentially result in a discrepancy between the trained policy and the optimal policy, as the policy directly depends on the value function in the reinforcement learning framework.