About me

I am currently a data scientist at CeADAR Ireland's Centre For Applied AI and previously worked as a postdoctoral researcher at Insight SFI Centre for Data Analytics at Dublin City University in Ireland. My PhD focused on the training of neural networks with supervision and computation constraints. I received my B.E. and M.E. in Telecommunications Engineering at Universitat Politècnica de Catalunya.

My primary research interest is the application and development of machine learning techniques to help us understand and interact with the world.

Selected publications

Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets
Paul Albert, Eric Arazo, Noel E O'Connor, Kevin McGuinness.
European Conference on Computer Vision (ECCV), 2022
[arXiv]

Segmentation Enhanced Lameness Detection in Dairy Cows from RGB and Depth Video.
Eric Arazo, Robin Aly, Kevin McGuinness.
Computer Vision and Pattern Recognition workshop (CVPRw), 2022
[arXiv]

Addressing out-of-distribution label noise in webly-labelled data.
Paul Albert, Diego Ortego, Eric Arazo, Noel E O'Connor, Kevin McGuinness.
Winter Conference on Applications of Computer Vision (WACV), 2022
[arXiv][Code]

How Important is Importance Sampling for Deep Budgeted Training?
Eric Arazo, Diego Ortego, Paul Albert, Noel E O'Connor, Kevin McGuinness.
British Machine Vision Conference (BMVC), 2021
[arXiv][Code]

Multi-Objective Interpolation Training for Robustness to Label Noise.
Diego Ortego, Eric Arazo, Paul Albert, Noel E O'Connor, Kevin McGuinness.
Computer Vision and Pattern Recognition (CVPR), 2021
[arXiv][Code]

ReLaB: Reliable Label Bootstrapping for Semi-Supervised Learning
Paul Albert, Diego Ortego, Eric Arazo, Noel E O'Connor, Kevin McGuinness
International Joint Conference on Neural Networks (IJCNN), 2021
[arXiv][Code]

Pseudo-labeling and confirmation bias in deep semi-supervised learning
Eric Arazo, Diego Ortego, Paul Albert, Noel E O’Connor, Kevin McGuinness
International Joint Conference on Neural Networks (IJCNN), 2020
[arXiv][Code]

Towards Robust Learning with Different Label Noise Distributions
Diego Ortego, Eric Arazo, Paul Albert, Noel E O'Connor, Kevin McGuinness
International Conference on Pattern Recognition (ICPR), 2020
[arXiv][Code]

Unsupervised label noise modeling and loss correction
Eric Arazo, Diego Ortego, Paul Albert, Noel E O'Connor, Kevin McGuinness
International Conference on Machine Learning (ICML), 2019
[arXiv][Code]

Improving Unsupervised Learning With Exemplar CNNs
E. Arazo, N. O'Connor, K. McGuinness
Irish Machine Vision and Image Processing Conference (IMVIP), 2019
[DORAS][Code]

Academic services

  • Conference reviewer: NeurIPS 2020, ACMR ICMR 2020, MMM 2021, ICCV 2021, ICMR 2021, WACV 2022, CVPR 2022, ECCV 2022, CVPR 2023, ICCV 2023, CVPR 2024
  • Journal reviewer: T-ASE, TMM, TPAMI, PR