YOLO-based Small-scaled Model for On-Shelf Availability in Retail

Abstract

On-shelf availability (OSA) in the retail industry plays a very crucial role in continuous sales. Product unavailability may lead to a bad impression on customers and reduce sales. The retail industry may continue to develop through the rapidly advancing technology era to thrive in a market where competition is increasingly tough. Along with technological advancements in recent decades, Artificial Intelligence has begun to be applied to support OSA, particularly using object detection technology. In this research, we develop a small-scaled object detection model based on four versions of You Only Look Once (YOLO) algorithm, namely YOLOv5-nano, YOLOv6-nano, YOLOv7-tiny, and YOLOv8-nano. The developed model can be used to support automatic detection of OSA. A small-scale model has developed in the sense of post-practical implementation through low-cost mobile applications. We also use the quantization method to reduce the model size, INT8 and FP16. This small-scaled model implementation also offers implementation flexibility. With a total of 7697 milk-based retail product images and 125 different product classes, the experiment results show that the developed YOLOv8-nano model, with a mAP50 score of 0.933 and an inference time of 13.4 ms, achieved the best performance.

Keywords

• small-scaled model
• yolo
• on-shelf availability
• retail
• deep learning