Papers › Deep Transfer Learning with Joint Adaptation Networks

Deep Transfer Learning with Joint Adaptation Networks

21 May 2016ICML 2017 8arXiv:1605.06636archive 2025-07-28

Mingsheng Long, Han Zhu, Jian-Min Wang, Michael. I. Jordan

Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain. In this paper, we present joint adaptation networks (JAN), which learn a transfer network by aligning the joint distributions of multiple domain-specific layers across domains based on a joint maximum mean discrepancy (JMMD) criterion. Adversarial training strategy is adopted to maximize JMMD such that the distributions of the source and target domains are made more distinguishable. Learning can be performed by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Experiments testify that our model yields state of the art results on standard datasets.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thuml/Transfer-Learning-Library mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Source Unsupervised Domain AdaptationTransfer Learning

Datasets

Introduced by this paper, per the archive.

ImageCLEF-DA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation HMDBfull-to-UCF JAN Accuracy 79.69 #3 of 5 Archive leaderboard report
Domain Adaptation UCF-to-HMDBfull JAN Accuracy 74.72 #3 of 5 Archive leaderboard report
Domain Adaptation VisDA2017 JAN Accuracy 58.3 #28 of 28 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home JAN [cite:ICML17JAN] Accuracy 76.8 #13 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections