Search papers, labs, and topics across Lattice.
Université Paris-Saclay, ENS Paris-Saclay
2
0
2
Removing stochastic noise from statistical regularizers leads to faster convergence and superior performance in Self-Supervised Learning tasks.
Gaussian embeddings might be suboptimal for self-supervised learning: enforcing hyperspherical uniformity in learned representations yields substantial gains in texture retrieval and ImageNet classification.
