A Scenario-Based Functional Testing Approach to Improving DNN Performance

TL;DR

This paper introduces a scenario-based iterative testing and retraining approach to improve deep neural network performance, demonstrated on an autonomous racing car perception system, with less resource use than full retraining.

Contribution

It presents a novel scenario-based testing and targeted transfer learning method for enhancing DNN performance efficiently.

Findings

Improved DNN performance on targeted scenarios.

Efficient enhancement with less resource consumption.

Effective diagnosis and treatment of weak scenarios.

Abstract

This paper proposes a scenario-based functional testing approach for enhancing the performance of machine learning (ML) applications. The proposed method is an iterative process that starts with testing the ML model on various scenarios to identify areas of weakness. It follows by a further testing on the suspected weak scenarios and statistically evaluate the model's performance on the scenarios to confirm the diagnosis. Once the diagnosis of weak scenarios is confirmed by test results, the treatment of the model is performed by retraining the model using a transfer learning technique with the original model as the base and applying a set of training data specifically targeting the treated scenarios plus a subset of training data selected at random from the original train dataset to prevent the so-call catastrophic forgetting effect. Finally, after the treatment, the model is assessed and evaluated again by testing on the treated scenarios as well as other scenarios to check if the treatment is effective and no side effect caused. The paper reports a case study with a real ML deep neural network (DNN) model, which is the perception system of an autonomous racing car. It is demonstrated that the method is effective in the sense that DNN model's performance can be improved. It provides an efficient method of enhancing ML model's performance with much less human and compute resource than retrain from scratch.