Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
This is an incremental survey paper summarizing existing methods for researchers in computer vision dealing with limited labeled data.
The paper reviews unsupervised domain adaptation methods in computer vision to address performance drops due to domain shift when transferring models from labeled source to unlabeled target domains, comparing non-deep and deep approaches without presenting new experimental results.
Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled target domain. Unfortunately, direct transfer across domains often performs poorly due to domain shift and dataset bias. Domain adaptation is the machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this paper, we summarize and compare the latest unsupervised domain adaptation methods in computer vision applications. We classify the non-deep approaches into sample re-weighting and intermediate subspace transformation categories, while the deep strategy includes discrepancy-based methods, adversarial generative models, adversarial discriminative models and reconstruction-based methods. We also discuss some potential directions.