Improving Domain Generalization by Learning without Forgetting: Application in Retail Checkout

Designing an automatic checkout system for retail stores at the human level accuracy is challenging due to similar appearance products and their various poses. This paper addresses the problem by proposing a method with a two-stage pipeline. The first stage detects class-agnostic items, and the seco...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Nguyen, Thuy C, Phan, Nam LH, Nguyen, Son T
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.07.2022
Subjects
Checkout
Domains
Error reduction
Retail stores
Online AccessGet full text

Cover

More Information
Summary:Designing an automatic checkout system for retail stores at the human level accuracy is challenging due to similar appearance products and their various poses. This paper addresses the problem by proposing a method with a two-stage pipeline. The first stage detects class-agnostic items, and the second one is dedicated to classify product categories. We also track the objects across video frames to avoid duplicated counting. One major challenge is the domain gap because the models are trained on synthetic data but tested on the real images. To reduce the error gap, we adopt domain generalization methods for the first-stage detector. In addition, model ensemble is used to enhance the robustness of the 2nd-stage classifier. The method is evaluated on the AI City challenge 2022 -- Track 4 and gets the F1 score \(40\%\) on the test A set. Code is released at the link https://github.com/cybercore-co-ltd/aicity22-track4.
ISSN:2331-8422