Semi-Supervised Object Detection Based on Dense Information Mining from Teacher Model

Recent advancements in semi-supervised object detection have shown promising results. However, the dense information predictions from the teacher model are often discarded. To address this issue, we propose the Pixel-level Contrastive Learning (PCL) module and the Regression Distribution Distillation (RDD) module. The PCL module effectively mines the dense classification information embedded in the teacher model, providing the student model with more precise supervisory signals. On the other hand, the RDD module leverages the dense regression information from the teacher model to explicitly supervise the regression branch of the student model. These modules collectively enhance the model's classification and regression capabilities. Experimental results on the COCO dataset demonstrate that our approach achieves satisfactory performance, validating its effectiveness in semi-supervised object detection tasks.