S4: Self-Supervised learning with Sparse-dense Sampling

Y Tian, W Zhang, P Su, Y Xu, P Zhuang, X **e… - Knowledge-Based …, 2024‏ - Elsevier
Self-supervised visual representation learning (SSL) attempts to extract significant features
from unlabeled datasets, alleviating the necessity for labor-intensive and time-consuming …

PooDLe: Pooled and dense self-supervised learning from naturalistic videos

AN Wang, C Hoang, Y **ong, Y LeCun… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Self-supervised learning has driven significant progress in learning from single-subject,
iconic images. However, there are still unanswered questions about the use of minimally …