Alexander Hepburn

According to our database, Alexander Hepburn authored at least 17 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

An Interactive Human-Machine Learning Interface for Collecting and Learning from Complex Annotations.

Jonathan Erskine, Matthew Clifford, Alexander Hepburn, Raúl Santos-Rodríguez

CoRR, 2024

Evaluating Perceptual Distances by Fitting Binomial Distributions to Two-Alternative Forced Choice Data.

Alexander Hepburn, Raúl Santos-Rodriguez, Javier Portilla

CoRR, 2024

2023

Data is Overrated: Perceptual Metrics Can Lead Learning in the Absence of Training Data.

Tashi Namgyal, Alexander Hepburn, Raúl Santos-Rodríguez, Valero Laparra, Jesus Malo

CoRR, 2023

What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics.

Tashi Namgyal, Alexander Hepburn, Raúl Santos-Rodríguez, Valero Laparra, Jesus Malo

CoRR, 2023

Disentangling the Link Between Image Statistics and Human Perception.

Alexander Hepburn, Valero Laparra, Raúl Santos-Rodríguez, Jesús Malo

CoRR, 2023

Identification, explanation and clinical evaluation of hospital patient subtypes.

Enrico Werner, Jeffrey N. Clark, Ranjeet S. Bhamber, Michael Ambler, Christopher P. Bourdeaux, Alexander Hepburn, Christopher J. McWilliams, Raúl Santos-Rodríguez

CoRR, 2023

Reconciling Training and Evaluation Objectives in Location Agnostic Surrogate Explainers.

Matthew Clifford, Jonathan Erskine, Alexander Hepburn, Peter A. Flach, Raúl Santos-Rodríguez

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

2022

What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components.

Kacper Sokol, Alexander Hepburn, Raúl Santos-Rodríguez, Peter A. Flach

CoRR, 2022

On the relation between statistical learning and perceptual distances.

Alexander Hepburn, Valero Laparra, Raúl Santos-Rodríguez, Johannes Ballé, Jesus Malo

Proceedings of the Tenth International Conference on Learning Representations, 2022

Orthonormal Convolutions for the Rotation Based Iterative Gaussianization.

Valero Laparra, Alexander Hepburn, Juan Emmanuel Johnson, Jesús Malo

Proceedings of the 2022 IEEE International Conference on Image Processing, 2022

Sampling Based On Natural Image Statistics Improves Local Surrogate Explainers.

Ricardo Kleinlein, Alexander Hepburn, Raúl Santos-Rodríguez, Fernando Fernández Martínez

Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021

Explainers in the Wild: Making Surrogate Explainers Robust to Distortions Through Perception.

Alexander Hepburn, Raúl Santos-Rodríguez

Proceedings of the 2021 IEEE International Conference on Image Processing, 2021

2020

FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems.

Kacper Sokol, Alexander Hepburn, Rafael Poyiadzi, Matthew Clifford, Raúl Santos-Rodríguez, Peter A. Flach

J. Open Source Softw., 2020

Enforcing perceptual consistency on Generative Adversarial Networks by using the Normalised Laplacian Pyramid Distance.

Alexander Hepburn, Valero Laparra, Ryan McConville, Raúl Santos-Rodríguez

Proceedings of the 2020 Northern Lights Deep Learning Workshop, 2020

Perceptnet: A Human Visual System Inspired Neural Network For Estimating Perceptual Distance.

Alexander Hepburn, Valero Laparra, Jesús Malo, Ryan McConville, Raúl Santos-Rodríguez

Proceedings of the IEEE International Conference on Image Processing, 2020

2019

bLIMEy: Surrogate Prediction Explanations Beyond LIME.

Kacper Sokol, Alexander Hepburn, Raúl Santos-Rodríguez, Peter A. Flach

CoRR, 2019

2018

Proper Losses for Learning with Example-Dependent Costs.

Alexander Hepburn, Ryan McConville, Raúl Santos-Rodríguez, Jesús Cid-Sueiro, Dario García-García

Proceedings of the Second International Workshop on Learning with Imbalanced Domains: Theory and Applications, 2018