Abstract:
Deep neural networks excel at many benchmark vision tasks thanks to large labeled training datasets. Obtaining large amounts of labeled data is costly and time-consuming in many applications. Many have tried to directly apply models trained on a large-scale labeled source domain to a sparsely labeled or unlabeled target domain to overcome limited labeled training data. Domain shift and dataset bias make direct domain transfer difficult. Domain adaptation (DA) is a machine learning paradigm that learns a model from a source domain that performs well on a related target domain. This article reviews the latest single-source deep unsupervised DA methods for visual tasks and discusses new research directions. We define DA strategies and benchmark datasets. We summarize and compare discrepancy-based, adversarial discriminative, adversarial generative, and self-supervision-based single-source unsupervised DA methods. Finally, we discuss future research challenges and solutions.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here