Arman Afrasiyabi

Hi! I am a PhD candidate at Université Laval and Mila.

I’m supervised by Jean-François Lalonde and Christian Gagné since September 2017, and my research is focused on meta-learning and representation learning. Three recent highlights of our research are:

• Associative alignment for few-shot image classification (ECCV-2020),
• Mixture-based feature space learning for few-shot image classification (ICCV-2021),
• Matching feature sets for few-shot image classification (CVPR-2022).

I am currently investigating contextual self-supervised learning for quick adaptations under the meta-learning context, and my research interests broadly are:

• Computer vision
• Deep learning, and unsupervised representation learning
• Machine learning (in general)
• Cognitive science