Search Results for author: Ian Mason

Found 8 papers, 4 papers with code

Task Arithmetic Through The Lens Of One-Shot Federated Learning

no code implementations27 Nov 2024 Zhixu Tao, Ian Mason, Sanjeev Kulkarni, Xavier Boix

In this paper, we examine Task Arithmetic for multi-task learning by framing it as a one-shot Federated Learning problem.

Federated Learning Task Arithmetic

Rethinking VLMs and LLMs for Image Classification

no code implementations3 Oct 2024 Avi Cooper, Keizo Kato, Chia-Hsien Shih, Hiroaki Yamane, Kasper Vinken, Kentaro Takemoto, Taro Sunagawa, Hao-Wei Yeh, Jin Yamanaka, Ian Mason, Xavier Boix

Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness.

Classification image-classification +2

Modularity Trumps Invariance for Compositional Robustness

1 code implementation15 Jun 2023 Ian Mason, Anirban Sarkar, Tomotake Sasaki, Xavier Boix

In this work we develop a compositional image classification task where, given a few elemental corruptions, models are asked to generalize to compositions of these corruptions.

Domain Generalization image-classification +1

DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds

1 code implementation ACM Transactions on Graphics 2022 Sebastian Starke, Ian Mason, Taku Komura

Learning the spatial-temporal structure of body movements is a fundamental problem for character motion synthesis.

Motion Synthesis

Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

1 code implementation12 Jan 2022 Ian Mason, Sebastian Starke, Taku Komura

In this work we present a style modelling system that uses an animation synthesis network to model motion content based on local motion phases.

Style Transfer

Unit-level surprise in neural networks

no code implementations NeurIPS Workshop ICBINB 2021 Cian Eastwood, Ian Mason, Chris Williams

To adapt to changes in real-world data distributions, neural networks must update their parameters.

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

1 code implementation ICLR 2022 Cian Eastwood, Ian Mason, Christopher K. I. Williams, Bernhard Schölkopf

Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level of feature-space class-separation in the target domain.

Source-Free Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.