← Search

Haoxuan Dou

2 accepted papers

2021

AutoSampling: Search for Effective Data Sampling Schedules

ICML 2021spotlight

Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to its inherent high-dimension as a hyper-parameter. In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training,…

Cited by 8SourcePDFScholar
2020

Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight

ECCV 2020poster

Transfer learning can boost the performance on the target task by leveraging the knowledge of the source domain. Recent works in neural architecture search (NAS), especially one-shot NAS, can aid transfer learning by establishing sufficient network search space. However, existing NAS methods tend to…

Cited by 7SourcePDFScholar