This article was contributed by Nikita Johnson.
The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically.
However, despite their appeal, such models often fail to distinguish synthetic images from real images, necessitating domain adaptation algorithms to manipulate these models before they can be successfully applied. Dilip Krishnan, Research Scientist at Google, is working on two approaches to the problem of unsupervised visual domain adaptation (both of which outperform current state-of-the-art methods.)
What you can find in the full article:
To read the original article, click here.
Top DSC Resources