Domain Transfer Network
TensorFlow implementation of unsupervised cross-domain image generation for transferring images between domains like SVHN to MNIST.
What is Domain Transfer Network?
Domain Transfer Network (DTN) is a TensorFlow implementation of unsupervised cross-domain image generation. It enables image-to-image translation between different visual domains without requiring paired training data, solving the problem of transferring visual styles across datasets like converting SVHN street view numbers to MNIST handwritten digits.
Machine learning researchers and developers working on computer vision, domain adaptation, and generative models who need to implement unsupervised image translation between domains.
Developers choose DTN because it provides a clean, reproducible implementation of a research paper's methodology, offers visual results of the transfer process, and handles complex domain adaptation tasks without paired data requirements.
Overview
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
Use Cases
Best For
- Implementing unsupervised domain adaptation research papers
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
