News

Abstract:

Handwriting recognition systems have achieved remarkable performance over the past several years with the advent of deep neural networks. For high-quality recognition, these models require large amounts of labeled training data, which can be difficult to obtain. Various methods to reduce this effort have been proposed in the realms of active and transfer learning, but not in combination. We propose a framework for fitting new handwriting recognition models that joins active and transfer learning into a unified framework. Empirical results show the superiority of our method compared to traditional active learning, transfer learning, or standard supervised training schemes.