Robust Visual Learning with Limited Labels
The recent flourish of deep learning in various visual learning tasks is largely credited to the rich and accessible labeled data. Nonetheless, massive label supervision remains a luxury for many real-world applications: It is costly and time-consuming to collect and annotate a large amount of train...
| Published: |
|
|---|---|
| Online Access: | http://hdl.handle.net/2047/D20409230 |