Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition
- It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link to the github repository of this report can be found here: https://github.com/agrija9/Deep-Unsupervised-Domain-Adaptation.
Document Type: | Preprint |
---|---|
Language: | English |
Author: | Alan Preciado-Grijalva, Venkata Santosh Sai Ramireddy Muthireddy |
Number of pages: | 7 |
DOI: | https://doi.org/10.48550/arXiv.2109.13420 |
ArXiv Id: | http://arxiv.org/abs/2109.13420 |
Publisher: | arXiv |
Date of first publication: | 2021/09/28 |
Keyword: | convolutional neural networks; domain adaptation; transfer learning; unsupervised learning |
Departments, institutes and facilities: | Fachbereich Informatik |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2021/10/04 |