Contrastive Learning (CL) is a paradigm designed for self-supervised representation learning which has been applied to unsupervised, weakly supervised and supervised problems. The objective in CL is to estimate a parametric mapping function that maps positive samples (semantically similar) close together in the representation space and negative samples (semantically dissimilar) far away from each other. In general, positive samples can be defined in different ways depending on the problem: transformations (i.e., augmentations) of the same image (unsupervised setting), samples belonging to the same class (supervised) or with similar image attributes (weakly-supervised). The definition of negative samples varies accordingly. In this talk, we will show how a metric learning approach for CL allows us to: 1- better formalize recent contrastive losses, such as InfoNCE and SupCon, 2- derive new losses for unsupervised, supervised, and weakly supervised problems, both classification and regression, and 3- propose new regularization terms for debiasing. Furthermore, leveraging the proposed metric learning approach and kernel theory, we will describe a novel loss, called decoupled uniformity, that allows the integration of prior knowledge, given either by generative models or weak attributes, and removes the positive-negative coupling problem, as in the InfoNCE loss. We validate the usefulness of the proposed losses on standard vision datasets and medical imaging data.
Pietro Gori is Maître de Conférences in Artificial Intelligence and Medical Imaging at Télécom Paris (IPParis) in the IMAGES group. He did his academic training with Inria at the ARAMIS Lab in Paris and then at Neurospin (CEA). Previous to that, he obtained a MSc in Mathematical Modelling and Computation from the DTU in Copenhagen and a MSc in Biomedical Engineering from the University of Padova. He participated to the development of the open source software suite deformetrica for statistical shape analysis and of the software platform Clinica for clinical neuroimaging studies. His research interests lie primarily in the fields of machine learning, AI, representation learning, medical imaging and computational anatomy.