Events

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.

Braden Hurl, Master’s candidate
David R. Cheriton School of Computer Science

This work introduces the Precise Synthetic Image and LiDAR (PreSIL) dataset for autonomous vehicle perception. Grand Theft Auto V (GTA V), a commercial video game, has a large, detailed world with realistic graphics, which provides a diverse data collection environment. Existing works creating synthetic LiDAR data for autonomous driving with GTA V have not released their datasets, rely on an in-game raycasting function which represents people as cylinders, and can fail to capture vehicles past 30 metres.

Nolan Shaw, Master’s candidate
David R. Cheriton School of Computer Science

In this work, I study the relationship between a local, intrinsic update mechanism and a synaptic, error-based learning mechansim in ANNs. I present a local intrinsic rule that I developed, dubbed IP, that was inspired by the Infomax rule. Like Infomax, this IP rule works by controlling the gain and bias of a neuron to regulate its rate of fire. I discuss the biological plausibility of this rule and compare it to batch normalisation.

Jaejun Lee, Master’s candidate
David R. Cheriton School of Computer Science

Used for simple voice commands and wake-word detection, keyword spotting (KWS) is the task of detecting pre-determined keywords in a stream of utterances. A common implementation of KWS involves transmitting audio samples over the network and detecting target keywords in the cloud with neural networks because on-device application development presents compatibility issues with various edge devices and provides limited supports for deep learning. Unfortunately, such an architecture can lead to unpleasant user experience because network latency is not deterministic. Furthermore, the client-server architecture raises privacy concerns because users lose control over the audio data once it leaves the edge device. 

Xin Lian, Master’s candidate
David R. Cheriton School of Computer Science

The problem of language alignment has long been an exciting topic for Natural Language Processing researchers. Current methods for learning cross-domain correspondences at the word level rely on distributed representations of words. Therefore, the recent development in the word computational linguistics and neural language modeling has led to the development of the so-called zero-shot learning paradigm.

Wei Tao Chen, Master’s candidate
David R. Cheriton School of Computer Science

Image semantic segmentation is an important problem in computer vision. However, training a deep neural network for semantic segmentation in supervised learning requires expensive manual labeling. Active learning (AL) addresses this problem by automatically selecting a subset of the dataset to label and iteratively improve the model. This minimizes labeling costs while maximizing performance. Yet, deep active learning for image segmentation has not been systematically studied in the literature. 

Ashish Gaurav, Master’s candidate
David R. Cheriton School of Computer Science

Continual learning is often confounded by “catastrophic forgetting” that prevents neural networks from learning tasks sequentially. In the case of real world classification systems that are safety-validated prior to deployment, it is essential to ensure that validated knowledge is retained.