Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition
This work addresses the problem of evaluating transfer learning's utility for researchers and practitioners in computer vision, showing it can be incremental or unnecessary in certain scenarios.
The paper investigated the effectiveness of deep transfer learning for character recognition tasks, finding that it did not provide significant performance advantages over traditional machine learning approaches in their experiments.
Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then retraining on a new one is called transfer learning. In this paper we analyse the effectiveness of using deep transfer learning for character recognition tasks. We perform three sets of experiments with varying levels of similarity between source and target tasks to investigate the behaviour of different types of knowledge transfer. We transfer both parameters and features and analyse their behaviour. Our results demonstrate that no significant advantage is gained by using a transfer learning approach over a traditional machine learning approach for our character recognition tasks. This suggests that using transfer learning does not necessarily presuppose a better performing model in all cases.