Unsupervised Domain Adaptation by Backpropagation

Victor Lempitsky

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 41 functions out of this paper's own repositories and ran 34 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• BalrajAshwath/Adversarial-Domain_Adaptation_Paper_Implementations
• Carl0520/DANN_pytorch-
• ChrisAllenMing/Mixup_for_UDA
• KeiraZhao/MDAN
• chenkang121/DANN
• erlendd/ddan
• ermolenkodev/da-ssd
• hanzhaoml/mdan
• jvanvugt/pytorch-domain-adaptation
• lancerane/Adversarial-domain-adaptation
• mashaan14/DANN-toy
• sroutray/da-ganin
• tachitachi/GradientReversal
• tadeephuy/GradientReversal
• Elman295/Unsupervised-Domain-Adaptation-by-Backpropagation-
• PaddlePaddle/PaddleSpeech
• adapt-python/adapt
• fungtion/DANN
• janfreyberg/pytorch-revgrad
• kevinmusgrave/pytorch-adapt
• theairbend3r/how-to-train-your-neural-net
• thuml/Transfer-Learning-Library

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled targetdomain data is necessary). As the training progresses, the approach promotes the emergence of "deep" features that are (i) discriminative for the main learning task on the source domain and (ii) invariant with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a simple new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation. Overall, the approach can be implemented with little effort using any of the deep-learning packages. The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-ofthe-art on Office datasets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1409.7495")
get_code_for_paper("1409.7495")
have("1409.7495")

Connect an agent — have() is free.