Low-Cost Transfer Learning of Face Tasks

John, Trupthi Ann and Dua, Isha and Balasubramanian, Vineeth N and C V, Jawahar (2019) Low-Cost Transfer Learning of Face Tasks. arXiv. pp. 1-13. (Submitted)

Preview

Text
1901.02675.pdf - Accepted Version
Download (2MB) | Preview

Abstract

Do we know what the different filters of a face network represent? Can we use this filter information to train other tasks without transfer learning? For instance, can age, head pose, emotion and other face related tasks be learned from face recognition network without transfer learning? Understanding the role of these filters allows us to transfer knowledge across tasks and take advantage of large data sets in related tasks. Given a pretrained network, we can infer which tasks the network generalizes for and the best way to transfer the information to a new task. We demonstrate a computationally inexpensive algorithm to reuse the filters of a face network for a task it was not trained for. Our analysis proves these attributes can be extracted with an accuracy comparable to what is obtained with transfer learning, but 10 times faster. We show that the information about other tasks is present in relatively small number of filters. We use these insights to do task specific pruning of a pretrained network. Our method gives significant compression ratios with reduction in size of 95% and computational reduction of 60%

[error in script]

IITH Creators: