Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios
This addresses the challenge of data scarcity and imbalance for small object detection in industrial applications, but it is incremental as it builds on existing methods with synthetic data and balancing techniques.
This study tackled the problem of poor performance of state-of-the-art object detection models on small objects in industrial scenarios by using synthetic data generation and a proportional class-balancing technique, resulting in improved model performance as demonstrated through comparative testing on YOLOv5, YOLOv7, and SSD.
Object Detection (OD) has proven to be a significant computer vision method in extracting localized class information and has multiple applications in the industry. Although many of the state-of-the-art (SOTA) OD models perform well on medium and large sized objects, they seem to under perform on small objects. In most of the industrial use cases, it is difficult to collect and annotate data for small objects, as it is time-consuming and prone to human errors. Additionally, those datasets are likely to be unbalanced and often result in an inefficient model convergence. To tackle this challenge, this study presents a novel approach that injects additional data points to improve the performance of the OD models. Using synthetic data generation, the difficulties in data collection and annotations for small object data points can be minimized and to create a dataset with balanced distribution. This paper discusses the effects of a simple proportional class-balancing technique, to enable better anchor matching of the OD models. A comparison was carried out on the performances of the SOTA OD models: YOLOv5, YOLOv7 and SSD, for combinations of real and synthetic datasets within an industrial use case.