
About me
In December 2023, I joined
CeADAR Ireland's Centre For Applied AI as an AI scientist II. We work on model efficiency and trustworthiness for multiple modalities of data and
address areas such as model compression, domain adaptation, and generative AI.
From 2021 to 2023, during my postdoctoral position at
Insight SFI Centre for Data Analytics at
Dublin City University in Ireland, I applied and developed AI techniques for time series analysis
and computer vision, video data and precision farming, computer vision applied to medical imaging, and traditional machine learning
techniques for water quality analysis.
During my PhD, I studied the training of neural networks under supervision and computation constraints focused on computer vision applications and developed algorithms to address key limitations in the field.
I received my B.E. and M.E. in Telecommunications Engineering from
Universitat Politècnica de Catalunya in Barcelona.
My primary research interest is the application and development of machine learning
techniques to enhance AI systems' understanding and interaction with the world, with a particular focus on building trustworthy and reliable AI solutions.
Selected publications
- Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation. Sidra Aleem, Fangyijie Wang, Mayug Maniparambil, Eric Arazo, Julia Dietlmeier, Kathleen Curran, Noel E O'Connor, Suzanne Little. Computer Vision and Pattern Recognition workshop (CVPRw), 2024
- ConvLoRA and AdaBN based Domain Adaptation via Self-Training. Sidra Aleem, Julia Dietlmeier, Eric Arazo, Suzanne Little. IEEE ISBI, 2024
- Self-Supervised and Semi-Supervised Polyp Segmentation using Synthetic Data. Enric Moreu, Eric Arazo, Kevin McGuinness, Noel E O'Connor. Int. Joint Conf. on Neural Networks (IJCNN), 2023
- Is your noise correction noisy? PLS: Robustness to label noise with two stage detection. Paul Albert, Eric Arazo, Tarun Kirshna, Noel E O'Connor, Kevin McGuinness. Winter Conf. on Applic. of Comp. Vision (WACV), 2023
- Cardiac Segmentation using Transfer Learning under Respiratory Motion Artifacts. Carles Garcia-Cabrera, Eric Arazo, Kathleen M Curran, Noel E O'Connor, Kevin McGuinness. Statistical Atlases and Computational Models Workshop, STACOM 2022 / MICCAI 2022
- 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
- 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
- Addressing out-of-distribution label noise in webly-labelled data. Paul Albert, Diego Ortego, Eric Arazo, Noel E O'Connor, Kevin McGuinness. Winter Conf. on Applic. of Comp. Vision (WACV), 2022
- 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
- Multi-Objective Interpolation Training for Robustness to Label Noise. Diego Ortego, Eric Arazo, Paul Albert, Noel E O'Connor, Kevin McGuinness. Comp. Vision and Pattern Recognition (CVPR), 2021
-
ReLaB: Reliable Label Bootstrapping for Semi-Supervised Learning. Paul Albert, Diego Ortego, Eric Arazo, Noel E O'Connor, Kevin McGuinness. Int. Joint Conf. on Neural Networks (IJCNN), 2021
- Pseudo-labeling and confirmation bias in deep semi-supervised learning. Eric Arazo, Diego Ortego, Paul Albert, Noel E O’Connor, Kevin McGuinness. Int. Joint Conf. on Neural Networks (IJCNN), 2020
- Towards Robust Learning with Different Label Noise Distributions. Diego Ortego, Eric Arazo, Paul Albert, Noel E O'Connor, Kevin McGuinness. International Conf. on Pattern Recognition (ICPR), 2020
- Unsupervised label noise modeling and loss correction. Eric Arazo, Diego Ortego, Paul Albert, Noel E O'Connor, Kevin McGuinness. International Conf. on Machine Learning (ICML), 2019
- Improving Unsupervised Learning With Exemplar CNNs. E. Arazo, N. O'Connor, K. McGuinnes. Irish Machine Vision and Image Processing Conference (IMVIP), 2019
Academic services
- Active conference reviewer since 2020: ACMR ICMR, MMM, ICMR, WACV, ECCV, ICCV, CVPR, NeurIPS.
- Journal reviewer: T-ASE, TMM, TPAMI, PR.
- Host and lecturer in the Deep Learning for Computer Vision conference in Dublin City University (May 2022).
- Lecturer in Deep Learning for Computer Vision Workshop (IPCV master) in Universidad Autónoma de Madrid (April 2023).
- Lecturer in the Data Science for Business workshop for EDHEC Business School (April 2024).
Projects/experience
- MANOLO - EU project on AI efficiency and trustworthiness.
- FOREWARN - EU project on ML applied to watterquality analysis.
- Medical imaging research - Application of computer vision techniques for segmentaiton of medical images.
- Precission farming - Industrial partnership to design and develop video and time series analysis pipeline.
- Regulation compliance - Industrial partnership to monitor text and image documents compliance with finantial regulations.
- Nutrient analysis - Innovation partnership with start-up company to apply ML to extract nutritional information from images.