TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspection

TL;DR

TinyDefectNet is a highly compact deep neural network designed for high-throughput visual quality inspection in manufacturing, achieving state-of-the-art accuracy with significantly reduced computational resources and enhanced deployment speed.

Contribution

The paper introduces TinyDefectNet, a novel compact neural network architecture optimized for manufacturing defect detection, combining high accuracy with low computational complexity.

Findings

Achieves state-of-the-art detection accuracy on NEU defect dataset.

Reduces architectural complexity by 52x and computational complexity by 11x.

Delivers 7.6x to 9x faster throughput on hardware deployment.

Abstract

A critical aspect in the manufacturing process is the visual quality inspection of manufactured components for defects and flaws. Human-only visual inspection can be very time-consuming and laborious, and is a significant bottleneck especially for high-throughput manufacturing scenarios. Given significant advances in the field of deep learning, automated visual quality inspection can lead to highly efficient and reliable detection of defects and flaws during the manufacturing process. However, deep learning-driven visual inspection methods often necessitate significant computational resources, thus limiting throughput and act as a bottleneck to widespread adoption for enabling smart factories. In this study, we investigated the utilization of a machine-driven design exploration approach to create TinyDefectNet, a highly compact deep convolutional network architecture tailored for high-throughput manufacturing visual quality inspection. TinyDefectNet comprises of just ~427K parameters and has a computational complexity of ~97M FLOPs, yet achieving a detection accuracy of a state-of-the-art architecture for the task of surface defect detection on the NEU defect benchmark dataset. As such, TinyDefectNet can achieve the same level of detection performance at 52$\times$ lower architectural complexity and 11x lower computational complexity. Furthermore, TinyDefectNet was deployed on an AMD EPYC 7R32, and achieved 7.6x faster throughput using the native Tensorflow environment and 9x faster throughput using AMD ZenDNN accelerator library. Finally, explainability-driven performance validation strategy was conducted to ensure correct decision-making behaviour was exhibited by TinyDefectNet to improve trust in its usage by operators and inspectors.