Systems and methods for contrastive learning with self-labeling refinement

由 ZHOU, Pan, XIONG, Caiming, HOI, Steven
出版 2022

A theory-driven self-labeling refinement method for contrastive representation learning

由 ZHOU, Pan, XIONG, Caiming, YUAN, Xiao-Tong
出版 2021

Prototypical contrastive learning of unsupervised representations

由 LI, Junnan, ZHOU, Pan, XIONG, Caiming, HOI, Steven C. H.
出版 2021

Theory-inspired path-regularized differential network architecture search

由 ZHOU, Pan, XIONG, Caiming, SOCHER, Richard, HOI, Steven C. H.
出版 2020

Unified training of universal time series forecasting transformers

由 WOO, Gerald, LIU, Chenghao, KUMAR, Akshat, XIONG, Caiming, SAVARESE, Silvio, SAHOO, Doyen
出版 2024

Towards theoretically understanding why SGD generalizes better than ADAM in deep learning

由 ZHOU, Pan, FENG, Jiashi, MA, Chao, XIONG, Caiming, HOI, Steven C. H., E, Weinan
出版 2020

Task similarity aware meta learning: Theory-inspired improvement on MAML

由 ZHOU, Pan, ZPU, Yingtian, YUAN, XiaoTong, FENG, Jiashi, XIONG, Caiming, HOI, Steven C. H.
出版 2021

Improving tail-class representation with centroid contrastive learning

由 Tiong, Anthony Meng Huat, Li, Junnan, Lin, Guosheng, Li, Boyang, Xiong, Caiming, Hoi, Steven C. H.
出版 2023

How important is the train-validation split in meta-learning?

由 BAI, Yu, CHEN, Minshuo, ZHOU, Pan, ZHAO, Tuo, LEE, D. Jason, KAKADE, Sham, WANG, Huan, XIONG, Caiming
出版 2021