Rate My Professor Brendan McCane

McCane's research interests include computer vision, pattern recognition, machine learning, biomedical imaging, robotics, and computer graphics. His current research focuses on theoretical understanding of the effectiveness of deep networks and self-learning for robots. He participates in the Otago AI Group, with contributions to reinforcement learning, support vector machines, convolutional neural networks, deep learning, catastrophic forgetting, and models of visual perception. Key publications include "Recovering Motion Fields: An Evaluation of Eight Optical Flow Algorithms" (1998), "On Benchmarking Optical Flow" (2001), "SIFT and SURF Performance Evaluation Against Various Image Deformations on Benchmark Dataset" (2011), "LOOP Descriptor: Local Optimal-Oriented Pattern" (2018), "Pseudo-Rehearsal: Achieving Deep Reinforcement Learning Without Catastrophic Forgetting" (2021), "Cross-modal Image Generation with Uncertainty Quantification from Echocardiogram to MRI" (2026, Methods), "Conditional Autoencoder for Generating Binary Neutron Star Waveforms with Tidal and Precession Effects" (2025, Physical Review D), and "Identification of Stochastic Gravitational Wave Backgrounds from Cosmic Strings Using Machine Learning" (2025, Physical Review D). He is a member of the University of Otago Scholarships and Prizes Committee.