In this paper we tackle the problem of Generalized Category Discovery (GCD). Specifically,
given a dataset with labelled and unlabelled images, the task is to cluster all images in the …

Meta-learning and other approaches to few-shot learning are widely studied for image
recognition, and are increasingly applied to other vision tasks such as pose estimation and …

Abstract Models pre-trained on large datasets such as ImageNet provide the de-facto
standard for transfer learning, with both supervised and self-supervised approaches proving …

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By
learning to remain invariant to applied data augmentations, methods such as SimCLR and …

Contrastive self-supervised learning has gained attention for its ability to create high-quality
representations from large unlabelled data sets. A key reason that these powerful features …

Masked Image Modeling (MIM) has emerged as a popular method for Self-Supervised
Learning (SSL) of visual representations. However, for high-level perception tasks, MIM …

Abstract Machine learning has undeniably achieved remarkable advances thanks to large
labelled datasets and supervised learning. However, this progress is constrained by the …

This thesis studies opportunities and risks associated with stochasticity in deep learning that
specifically manifest in the context of adversarial robustness and neural architecture search …

Meta-learning in the broader context concerns how an agent learns about their own
learning, allowing them to improve their learning process. Learning how to learn is not only …

Models trained with self-supervised learning objectives have recently matched or surpassed
models trained with traditional supervised object recognition in their ability to predict neural …