Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
Multi-view Granular-ball Contrastive Clustering
Peng Su, Shudong Huang, Weihong Ma +2
Previous multi-view contrastive learning methods typically operate at two scales: instance-level and cluster-level. Instance-level approaches construct positive and negative pairs…
cs.LG2024
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
Junlin He, Jinxiao Du, Wei Ma
Self-supervised learning (SSL) has rapidly advanced in recent years, approaching the performance of its supervised counterparts through the extraction of representations from unlab…
cs.LG2024
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
Junlin He, Jinxiao Du, Susu Xu +1
Multi-View Representation Learning (MVRL) aims to learn a unified representation of an object from multi-view data. Deep Canonical Correlation Analysis (DCCA) and its variants shar…