Now showing items 21-28 of 28

    • Safety-Oriented Stability Biases for Continual Learning 

      Gaurav, Ashish (University of Waterloo, 2020-01-24)
      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 ...
    • Switching GAN-based Image Filters to Improve Perception for Autonomous Driving 

      Masud, Zarif (University of Waterloo, 2019-10-24)
      Autonomous driving holds the potential to increase human productivity, reduce accidents caused by human errors, allow better utilization of roads, reduce traffic accidents and congestion, free up parking space and provide ...
    • Towards Object Re-identification from Point Clouds for 3D MOT 

      Thérien, Benjamin (University of Waterloo, 2023-04-21)
      This thesis studies the problem of object re-identification (ReID) in a 3D multi-object tracking (MOT) context, by learning to match pairs of objects from cropped (e.g., using their predicted 3D bounding boxes) point cloud ...
    • Towards Pixel-Level OOD Detection for Semantic Segmentation 

      Angus, Matt (University of Waterloo, 2019-08-30)
      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 ...
    • Training Reject-Classifiers for Out-of-distribution Detection via Explicit Boundary Sample Generation 

      Vernekar, Sachin (University of Waterloo, 2020-01-24)
      Discriminatively trained neural classifiers can be trusted only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid ...
    • Transferring Pareto Frontiers across Heterogeneous Hardware Environments 

      Valov, Pavel (University of Waterloo, 2020-09-14)
      Configurable software systems provide options that affect functional and non-functional system properties. Selection of options forms system configurations with corresponding properties values. Nowadays configurable software ...
    • Understanding and Enhancing CDCL-based SAT Solvers 

      Zulkoski, Edward (University of Waterloo, 2018-08-02)
      Modern conflict-driven clause-learning (CDCL) Boolean satisfiability (SAT) solvers routinely solve formulas from industrial domains with millions of variables and clauses, despite the Boolean satisfiability problem being ...
    • WiseBench: A Motion Planning Benchmarking Framework for Autonomous Vehicles 

      Ilievski, Marko (University of Waterloo, 2020-10-01)
      Rapid advances in every sphere of autonomous driving technology have intensified the need to be able to benchmark and compare different approaches. While many benchmarking tools tailored to different sub-systems of an ...

      UWSpace

      University of Waterloo Library
      200 University Avenue West
      Waterloo, Ontario, Canada N2L 3G1
      519 888 4883

      All items in UWSpace are protected by copyright, with all rights reserved.

      DSpace software

      Service outages