Computer Vision Meetup: Retail Supply Chain Computer Vision Apps

Training data for product recognition within a large retail supply chain context is hard to get to scale as its dynamic in nature, with new products being introduced frequently. Supervised learning models rely on the training data and this problem becomes significant with the scale of the machine learning models. In this talk, Tarik will present a method based on creating a digital twin of the fulfillment or a distribution center facility and generating photorealistic digital assets to train and optimize the classification model to be deployed in the real world. The performance of the training process is then used in a feedback loop to adjust the synthetic data generator until an acceptable result is achieved. Furthermore, he'll share his deployment orchestration methodology over a large number of compute nodes. This method can also be extended to product inspection and other more complex computer vision tasks.

Tarik Hammadou has been a Senior Developer Relations Manager at NVIDIA since 2019. He's the author/co-author of over 20 journal and conference papers, and holds several patents in the area of image processing and sensors.

Read a summary of this presentation in the recap blog post:

Join the Computer Vision Meetup closest to you:

This video was recorded on Nov 10, 2022 at the virtual Computer Vision Meetup