Test Input Validation for Vision-based DL Systems: An Active Learning Approach

TL;DR

This paper introduces an active learning-based method utilizing multiple image comparison metrics to validate test inputs for vision-based deep learning systems, significantly improving accuracy and reducing manual effort compared to existing methods.

Contribution

It presents a novel multi-metric, active learning approach for automated validation of test inputs in vision-based DL systems, outperforming state-of-the-art methods in accuracy and effort efficiency.

Findings

Achieves an average accuracy of 97% in test input validation.

Outperforms baselines with at least 12.9% higher accuracy.

Provides practical accuracy-effort trade-offs validated on industrial and public datasets.

Abstract

Testing deep learning (DL) systems requires extensive and diverse, yet valid, test inputs. While synthetic test input generation methods, such as metamorphic testing, are widely used for DL testing, they risk introducing invalid inputs that do not accurately reflect real-world scenarios. Invalid test inputs can lead to misleading results. Hence, there is a need for automated validation of test inputs to ensure effective assessment of DL systems. In this paper, we propose a test input validation approach for vision-based DL systems. Our approach uses active learning to balance the trade-off between accuracy and the manual effort required for test input validation. Further, by employing multiple image-comparison metrics, it achieves better results in classifying valid and invalid test inputs compared to methods that rely on single metrics. We evaluate our approach using an industrial and a public-domain dataset. Our evaluation shows that our multi-metric, active learning-based approach produces several optimal accuracy-effort trade-offs, including those deemed practical and desirable by our industry partner. Furthermore, provided with the same level of manual effort, our approach is significantly more accurate than two state-of-the-art test input validation methods, achieving an average accuracy of 97%. Specifically, the use of multiple metrics, rather than a single metric, results in an average improvement of at least 5.4% in overall accuracy compared to the state-of-the-art baselines. Incorporating an active learning loop for test input validation yields an additional 7.5% improvement in average accuracy, bringing the overall average improvement of our approach to at least 12.9% compared to the baselines.