Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar +2
Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view…
cs.CV2022
Global-Local Self-Distillation for Visual Representation Learning
Tim Lebailly, Tinne Tuytelaars
The downstream accuracy of self-supervised methods is tightly linked to the proxy task solved during training and the quality of the gradients extracted from it. Richer and more me…