Optimizing YOLOv7 for Semiconductor Defect Detection

TL;DR

This paper improves semiconductor defect detection by optimizing YOLOv7 hyperparameters and ensembling strategies, achieving a 10% increase in mean Average Precision over the default model.

Contribution

It systematically evaluates hyperparameters and ensembling methods for YOLOv7, demonstrating significant performance gains in semiconductor defect detection.

Findings

Random vertical flipping improves AP by 3%.

Ensembling with Weighted Box Fusion enhances mAP by 10%.

Default YOLOv7 outperforms previous RetinaNet models.

Abstract

The field of object detection using Deep Learning (DL) is constantly evolving with many new techniques and models being proposed. YOLOv7 is a state-of-the-art object detector based on the YOLO family of models which have become popular for industrial applications. One such possible application domain can be semiconductor defect inspection. The performance of any machine learning model depends on its hyperparameters. Furthermore, combining predictions of one or more models in different ways can also affect performance. In this research, we experiment with YOLOv7, a recently proposed, state-of-the-art object detector, by training and evaluating models with different hyperparameters to investigate which ones improve performance in terms of detection precision for semiconductor line space pattern defects. The base YOLOv7 model with default hyperparameters and Non Maximum Suppression (NMS) prediction combining outperforms all RetinaNet models from previous work in terms of mean Average Precision (mAP). We find that vertically flipping images randomly during training yields a 3% improvement in the mean AP of all defect classes. Other hyperparameter values improved AP only for certain classes compared to the default model. Combining models that achieve the best AP for different defect classes was found to be an effective ensembling strategy. Combining predictions from ensembles using Weighted Box Fusion (WBF) prediction gave the best performance. The best ensemble with WBF improved on the mAP of the default model by 10%.