Exploring the Efficacy of Transfer Learning in Mining Image-Based Software Artifacts

TL;DR

This paper investigates how transfer learning, using models pre-trained on non-software data, can effectively classify software UML diagrams, especially when training data is limited, demonstrating its practical advantages.

Contribution

It demonstrates the successful application of transfer learning from non-software domains to software artifact classification, highlighting its effectiveness with small datasets.

Findings

Transfer learning improves classification performance with limited data.

Pre-trained models outperform non-transfer models on small and medium datasets.

Transfer learning is a viable alternative to custom architectures when data is scarce.

Abstract

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software UML diagrams. Our experimental results show training reacts positively to transfer learning as related to sample size, even though the pre-trained model was not exposed to training instances from the software domain. We contrast the transferred network with other networks to show its advantage on different sized training sets, which indicates that transfer learning is equally effective to custom deep architectures when large amounts of training data is not available.