GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding

arXiv:2403.09639v1 Announce Type: new
Abstract: Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two distinct views as positive pairs and unmatched points as negative pairs. However, this approach often results in semantically identical points having dissimilar representations, leading to a high number of false negatives and introducing a "semantic conflict" problem. To address this issue, we propose GroupContrast, a …

abstract arxiv cs.cv discrimination however learn negative positive representation representation learning results scale semantic type understanding