Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products

TL;DR

This paper presents a weakly supervised approach for instance segmentation of supermarket products, reducing annotation effort by automatically generating training data from minimal labels, and augmenting it to mimic real-world variations.

Contribution

It introduces a novel system that automatically segments objects using only class labels and enhances training data with augmentation, improving efficiency in grocery product segmentation.

Findings

Significant reduction in annotation effort.

Effective automatic segmentation from class labels.

Improved robustness through data augmentation.

Abstract

Grocery stores have thousands of products that are usually identified using barcodes with a human in the loop. For automated checkout systems, it is necessary to count and classify the groceries efficiently and robustly. One possibility is to use a deep learning algorithm for instance-aware semantic segmentation. Such methods achieve high accuracies but require a large amount of annotated training data. We propose a system to generate the training annotations in a weakly supervised manner, drastically reducing the labeling effort. We assume that for each training image, only the object class is known. The system automatically segments the corresponding object from the background. The obtained training data is augmented to simulate variations similar to those seen in real-world setups.