Systems and methods for contrastive learning with self-labeling refinement

بواسطة ZHOU, Pan, XIONG, Caiming, HOI, Steven
منشور في 2022

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

بواسطة ZHOU, Pan, XIONG, Caiming, YUAN, Xiao-Tong
منشور في 2021

Prototypical contrastive learning of unsupervised representations

بواسطة LI, Junnan, ZHOU, Pan, XIONG, Caiming, HOI, Steven C. H.
منشور في 2021

Theory-inspired path-regularized differential network architecture search

بواسطة ZHOU, Pan, XIONG, Caiming, SOCHER, Richard, HOI, Steven C. H.
منشور في 2020

Unified training of universal time series forecasting transformers

بواسطة WOO, Gerald, LIU, Chenghao, KUMAR, Akshat, XIONG, Caiming, SAVARESE, Silvio, SAHOO, Doyen
منشور في 2024

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

بواسطة ZHOU, Pan, FENG, Jiashi, MA, Chao, XIONG, Caiming, HOI, Steven C. H., E, Weinan
منشور في 2020

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

بواسطة ZHOU, Pan, ZPU, Yingtian, YUAN, XiaoTong, FENG, Jiashi, XIONG, Caiming, HOI, Steven C. H.
منشور في 2021

Improving tail-class representation with centroid contrastive learning

بواسطة Tiong, Anthony Meng Huat, Li, Junnan, Lin, Guosheng, Li, Boyang, Xiong, Caiming, Hoi, Steven C. H.
منشور في 2023

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

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