# Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

arXiv: https://arxiv.org/abs/2001.00448 · HTML: https://mlsanity.com/paper/2001.00448/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2020.

## Built on by (most cited first, 3 of 3)

- [Investigating Transfer Learning in Graph Neural Networks](https://mlsanity.com/paper/2202.00740/) (2022)
- [Improving Cause-of-Death Classification from Verbal Autopsy Reports](https://mlsanity.com/paper/2210.17161/) (2022)
- [Knowledge Graph Fusion for Language Model Fine-tuning](https://mlsanity.com/paper/2206.14574/) (2022)

## Abstract (arXiv)

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.