Large-Margin Contrastive Learning with Distance Polarization Regularizer
Shuo Chen 1 Gang Niu 1 Chen Gong 2 Jun Li 2 Jian Yang 2 Masashi Sugiyama 1 3
Abstract Intra/Inter-Cluster Distance Enlargement Polarization
Contrastive learning (CL) pretrains models in a
pairwise manner, where given a data point, other
data points are all regarded as dissimilar, includ-
ing some that are semantically similar. The issue
has been add ...


雷达卡




京公网安备 11010802022788号







