papers AI Learner
The Github is limit! Click to go to the new site.

Low-Cost Transfer Learning of Face Tasks

2019-01-09
Thrupthi Ann John, Isha Dua, Vineeth N Balasubramanian, C. V. Jawahar

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.02675

PDF

http://arxiv.org/pdf/1901.02675


Similar Posts

Comments