M
Mingsheng Long
Researcher at Tsinghua University
Publications - 167
Citations - 24990
Mingsheng Long is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Domain (software engineering). The author has an hindex of 54, co-authored 143 publications receiving 17044 citations. Previous affiliations of Mingsheng Long include Shanghai Jiao Tong University & University of California, Berkeley.
Papers
More filters
Posted Content
Learning Transferable Features with Deep Adaptation Networks
TL;DR: A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding.
Proceedings Article
Deep transfer learning with joint adaptation networks
TL;DR: JAN as mentioned in this paper aligns the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion to make the distributions of the source and target domains more distinguishable.
Proceedings ArticleDOI
Transfer Feature Learning with Joint Distribution Adaptation
TL;DR: JDA aims to jointly adapt both the marginal distribution and conditional distribution in a principled dimensionality reduction procedure, and construct new feature representation that is effective and robust for substantial distribution difference.
Proceedings Article
Learning Transferable Features with Deep Adaptation Networks
TL;DR: Deep Adaptation Network (DAN) as mentioned in this paper embeds hidden representations of all task-specific layers in a reproducing kernel Hilbert space where the mean embeddings of different domain distributions can be explicitly matched.
Proceedings Article
Unsupervised domain adaptation with residual transfer networks
TL;DR: Empirical evidence shows that the new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeledData in the target domain outperforms state of the art methods on standard domain adaptation benchmarks.