Semi-supervised Learning for Dense Object Detection in Retail Scenes

TL;DR

This paper introduces a semi-supervised learning approach using noisy student methodology to improve dense object detection in retail scenes, reducing annotation costs and leveraging unlabeled data effectively.

Contribution

It adapts noisy student self-supervised learning to dense object detection in retail scenes, demonstrating improved performance with more unlabeled data.

Findings

Enhanced detection accuracy with semi-supervised training

Performance improves as more unlabeled data is used

Achieves state-of-the-art results in dense retail object detection

Abstract

Retail scenes usually contain densely packed high number of objects in each image. Standard object detection techniques use fully supervised training methodology. This is highly costly as annotating a large dense retail object detection dataset involves an order of magnitude more effort compared to standard datasets. Hence, we propose semi-supervised learning to effectively use the large amount of unlabeled data available in the retail domain. We adapt a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection. We show that using unlabeled data with the noisy student training methodology, we can improve the state of the art on precise detection of objects in densely packed retail scenes. We also show that performance of the model increases as you increase the amount of unlabeled data.