Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training

Understand

This study delves into semi-supervised object detection (SSOD) to improve detector performance with additional unlabeled data.

• State-of-the-art SSOD performance has been achieved recently by self-training, in which training supervision consists of ground truths and pseudo-labels.
• In current studies, we observe that class imbalance in SSOD severely impedes the effectiveness of self-training.
• To address the class imbalance, we propose adaptive class-rebalancing self-training (ACRST) with a novel memory module called CropBank.