Publications

Ian Mason, Anirban Sarkar, Tomotake Sasaki, Xavier Boix, Modularity Trumps Invariance for Compositional Robustness, ArXiv Preprint, 2023. [PDF] [Bibtex] [Code]

Anirban Sarkar, Matthew Groth, Ian Mason, Tomotake Sasaki, Xavier Boix, Deephys: Deep Electrophysiology, Debugging Neural Networks under Distribution Shifts, ArXiv Preprint, 2023. [Website] [PDF] [Bibtex]

Sebastian Starke, Ian Mason, Taku Komura, DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds, SIGGRAPH/ACM Transactions on Graphics, 2022. [PDF] [Bibtex] [Project Page] [Award]

Cian Eastwood*, Ian Mason*, Christopher K. I. Williams, Bernhard Schölkopf, Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration, ICLR (Spotlight), 2022. (*Joint First Author). [PDF] [Bibtex] [Code]

Ian Mason, Sebastian Starke, Taku Komura, Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases, i3D/ACM on Computer Graphics and Interactive Techniques, 2022. [PDF] [Bibtex] [Data] [Code]

Cian Eastwood*, Ian Mason*, Christopher K. I. Williams, Unit-level Surprise in Neural Networks, NeurIPS 2021 Workshop, I (Still) Can’t Believe It’s Not Better/Proceedings of Machine Learning Research, 2021. (*Joint First Author). [PDF] [Bibtex] [Poster] [Award]

Ian Mason, Sebastian Starke, He Zhang, Hakan Bilen, Taku Komura, Few-shot Learning of Homogeneous Human Locomotion Styles, Computer Graphics Forum, 37(7), 2018. [PDF] [Bibtex] [Code] [Video] [Award]

PhD Thesis

Ian Mason, Few-shot Learning in Changing Domains, PhD Thesis, The University of Edinburgh, 2021. [PDF] [Bibtex]