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

TL;DR

This paper presents a two-stage approach for retail checkout automation that combines domain generalization and ensemble methods to improve accuracy in real-world scenarios, addressing domain gaps between synthetic training data and real images.

Contribution

It introduces a novel two-stage pipeline with domain generalization techniques and model ensemble to enhance retail checkout accuracy under domain shift.

Findings

Achieved 40% F1 score on AI City challenge 2022 test set.

Effectively reduced domain gap between synthetic and real images.

Demonstrated robustness through model ensemble methods.

Abstract

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.