Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition
This work addresses the problem of domain shift in image recognition for researchers, but it is incremental as it only compares existing methods.
The paper evaluated four unsupervised domain adaptation techniques for image classification on the Office-31 dataset, finding that CDAN+E performed best with an accuracy of 86.2%.
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.