Top-performing deep architectures are trained on massive amounts of labeled data . 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 . 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 . 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-of-the-art on Office datasets. The resulting augmented architecture can be trained using standard backpropagation. It can be easily implemented using any deep learning packages. Overall, The approach has been described by the authors of The Open University of Science and The University of New York University of Cambridge University’s Open University’s Deep

Links: PDF - Abstract

Code :

https://github.com/Carl0520/DANN_pytorch-
https://github.com/ChrisAllenMing/Mixup_for_UDA
https://github.com/KeiraZhao/MDAN
https://github.com/erlendd/ddan
https://github.com/fungtion/DANN
https://github.com/jvanvugt/pytorch-domain-adaptation
https://github.com/lancerane/Adversarial-domain-adaptation
https://github.com/tachitachi/GradientReversal
https://github.com/theairbend3r/how-to-train-your-neural-net/blob/master/pytorch/computer_vision/domain_adaptation/gradient_reverse_layer.ipynb

Keywords : adaptation - deep - university - domain - approach -

Leave a Reply

Your email address will not be published. Required fields are marked *