I am a Postdoctoral Researcher at Inria Saclay, where I am part of the MIND (Models and Inference for Neuroimaging Data) team. My work lies at the intersection of deep learning, neuroimaging, and neuroscience. I aim to develop models that learn robust, generalizable representations of the brain from large-scale datasets, supporting both clinical neuroscience and cognitive modeling.

Before joining Inria, I was a postdoctoral researcher at University of Turin, Italy, in the EIDOS group at the Computer Science Department, working on deep learning for medical imaging, with interests on contrastive learning, neuroimaging, multimodality, debiasing and robustness. I received a double Ph.D. from Télécom Paris (Institut Polytechnique de Paris) and University of Turin in 2023, supervised by Pietro Gori (Télécom Paris) and Marco Grangetto (University of Turin).

News:

• Jan. 2025: I am currently a Visiting Researcher at Inria MIND with Prof. Demian Wassermann, to study the connection between functional connectivity and cognition using contrastive learning.
• Dec. 2024: I am happy to announce that I am now a member of ELLIS Society 🎉!
• Mar. 2024: I am member of the newborn Asl To3 Radiomics Lab in Rivoli, Italy.

Ongoing Research

Here is a summary of main main ongoing activities. If you are interested in collaborations do not hesitate to contact me!

• Foundation models / Neuroimaging Learning generalizable representations from large cohorts of neuroimaging data with the aim of transferring knowledge to smaller clinical groups with different conditions (e.g. neurodegenerative and psychiatric disorders). Relevant work: https://arxiv.org/abs/2408.07079 (AnatCL)
• Multimodal Learning Improving representations by leveraging cross-modal interaction (e.g. using text to learn novel visual concepts https://arxiv.org/abs/2411.15611)
• Debiasing and Collateral Learning Learning unbiased models from biased data, both in a supervised or unsupervised fashion. Also providing human-interpretable descriptions of spurious correlations in the data (https://arxiv.org/abs/2408.09570)

Positions

• Jan. 2025 - now Visiting Researcher at Inria MIND
• Dec. 2023 - now Postdoctoral Researcher in deep learning for medical imaging (University of Turin)

Education

• 2020-2023 Ph.D. in Computer Science at Télécom Paris, France (cotutelle with University of Turin, Italy), with the thesis Collateral-Free Learning of Deep Representations: From Natural Images to Biomedical Applications.
• 2018-2020 Master’s degree in Artificial Intelligence at University of Turin, Italy

Selected Publications

• Anatomical foundation models for brain MRIs, C. A. Barbano, M. Brunello, B. Dufumier, M. Grangetto. Pattern Recognition Letters, 2025. [Paper]
• Contrastive learning for regression in multi‑site brain age prediction (Best poster award), C. A. Barbano, B. Dufumier, E. Duchesnay, M. Grangetto, and P. Gori. ISBI, 2023. [Paper]
• Unbiased Supervised Contrastive Learning, C. A. Barbano, B. Dufumier, E. Tartaglione, M. Grangetto, and P. Gori. ICLR, 2023. [Paper]
• Integrating Prior Knowledge in Contrastive Learning with Kernel, B. Dufumier, C. A. Barbano, R. [Paper] Louiset, E. Duchesnay, and P. Gori. ICML, 2023
• End: Entangling and disentangling deep representations for bias correction, E. Tartaglione, C. A. Barbano, and M. Grangetto. CVPR, 2021. [Paper]