Semi-supervised Learning for Dense Object Detection in Retail Scenes
This addresses the high annotation costs for dense retail object detection, offering a practical solution for retail applications.
The paper tackles the problem of dense object detection in retail scenes by proposing a semi-supervised learning approach, resulting in improved state-of-the-art performance with gains that scale with the amount of unlabeled data used.
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.