Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts

no code implementations • 3 Dec 2023 • Eashan Adhikarla, Kai Zhang, Jun Yu, Lichao Sun, John Nicholson, Brian D. Davison

As a result, it raises concerns about the overall robustness of the machine learning techniques for computer vision applications that are deployed publicly for consumers.

Data Augmentation Transfer Learning

A Kernel-Based Approach for Modelling Gaussian Processes with Functional Information

no code implementations • 26 Jan 2022 • John Nicholson, Peter Kiessler, D. Andrew Brown

For example, boundary value problems contain information on the boundary of a domain, which is an uncountable collection of points that cannot be incorporated into typical Gaussian process techniques.

Gaussian Processes Uncertainty Quantification

A cancellation theorem for modules over integral group rings

no code implementations • 1 Jul 2018 • John Nicholson

A long standing problem, which has its roots in low-dimensional homotopy theory, is to classify all finite groups $G$ for which the integral group ring $\mathbb{Z}G$ has stably free cancellation (SFC).

K-Theory and Homology Group Theory Representation Theory 20C05, 19B28, 19A13