Deep Transfer Learning

We study transfer learning, which aims to adapt previously gained knowledge to small scale problems. Transfer from very deep architectures may cause overfitting. We investigate CNN pruning for transfer.

Poster: https://drive.google.com/file/d/1b3BOGx4UQ2dr_lva4kCAFhGylEX4K82a/view?usp=sharing

Video: https://drive.google.com/file/d/1Sau94hldTGY0aaR7DUaEQdI4Ye72RJ5p/view?usp=sharing