activity
20132023
most citedDash: Semi-Supervised Learning with Dynamic Thresholding

52 citations · 153 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2022★ 1 cited

Semantic Data Augmentation based Distance Metric Learning for Domain Generalization

Mengzhu Wang, Jianlong Yuan, Qi Qian +2

Domain generalization (DG) aims to learn a model on one or more different but related source domains that could be generalized into an unseen target domain. Existing DG methods try…

cs.LG2021★ 52 cited

Dash: Semi-Supervised Learning with Dynamic Thresholding

Yi Xu, Lei Shang, Jinxing Ye +5

While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use eith…

cs.LG2021

Why Does Multi-Epoch Training Help?

Yi Xu, Qi Qian, Hao Li +1

Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in e…

cs.LG2021

A Theoretical Analysis of Learning with Noisily Labeled Data

Yi Xu, Qi Qian, Hao Li +1

Noisy labels are very common in deep supervised learning. Although many studies tend to improve the robustness of deep training for noisy labels, rare works focus on theoretically…

cs.LG2020★ 13 cited

WeMix: How to Better Utilize Data Augmentation

Yi Xu, Asaf Noy, Ming Lin +3

Data augmentation is a widely used training trick in deep learning to improve the network generalization ability. Despite many encouraging results, several recent studies did point…

cs.LG2020

Improved Knowledge Distillation via Full Kernel Matrix Transfer

Qi Qian, Hao Li, Juhua Hu

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model…