VisionAndGraphics

Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen …

Hyperbolic spaces have emerged as an effective manifold to learn representations due to their ability to efficiently represent …

While many Machine Learning methods were developed or transposed on Riemannian manifolds to tackle data with known non Euclidean …

We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to …