Rethinking Pseudo Labels for Semi-Supervised Object Detection
This work addresses critical issues in semi-supervised object detection for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of localization precision and class imbalance in semi-supervised object detection by introducing certainty-aware pseudo labels, improving state-of-the-art performance by 1-2% AP on COCO and PASCAL VOC and boosting supervised baselines by up to 10% AP with limited labeled data.
Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels, there is a lack of consideration in localization precision and amplified class imbalance, both of which are critical for detection tasks. In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels. This is achieved by converting conventional localization as a classification task followed by refinement. Conditioned on classification and localization quality scores, we dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Extensive experiments demonstrate that our method improves state-of-the-art SSOD performance by 1-2% AP on COCO and PASCAL VOC while being orthogonal and complementary to most existing methods. In the limited-annotation regime, our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.