Applying the Lower-Biased Teacher Model in Semi-Supervised Object Detection

TL;DR

The paper introduces the Lower Biased Teacher model, which enhances semi-supervised object detection by integrating localization loss to improve pseudo-label accuracy, addressing class imbalance and bounding box errors.

Contribution

It presents a novel Lower Biased Teacher model that incorporates localization loss, significantly improving pseudo-label quality in semi-supervised object detection.

Findings

Higher mAP scores on multiple datasets

Reduced pseudo-label bias from class imbalance

Mitigated errors from incorrect bounding boxes

Abstract

I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into the teacher model, which significantly improves the accuracy of pseudo-label generation. By addressing key issues such as class imbalance and the precision of bounding boxes, the Lower Biased Teacher model demonstrates superior performance in object detection tasks. Extensive experiments on multiple semi-supervised object detection datasets show that the Lower Biased Teacher model not only reduces the pseudo-labeling bias caused by class imbalances but also mitigates errors arising from incorrect bounding boxes. As a result, the model achieves higher mAP scores and more reliable detection outcomes compared to existing methods. This research underscores the importance of accurate pseudo-label generation and provides a robust framework for future advancements in semi-supervised learning for object detection.