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

While self-training achieves state-of-the-art results in semisupervised object detection (SSOD), it severely suffers from foreground-background and foreground-foreground imbalances in SSOD. In this paper, we propose an Adaptive Class- Rebalancing Self-Training (ACRST) with a novel memory module called CropBank to alleviate these imbalances and generate unbiased pseudo-labels. Besides, we observe that both self-training and data-rebalancing procedures suffer from noisy pseudo-labels in SSOD. Therefore, we contribute a simple yet effective two-stage pseudo-label filtering scheme to obtain accurate supervision. Our method achieves competitive performance on MS-COCO and VOC benchmarks. When using only 1% labeled data of MS-COCO, our method achieves 17. 02 mAP improvement over the supervised method and 5. 32 mAP gains compared with state-ofthe-arts.

Authors

• Fangyuan Zhang Tsinghua University
• Tianxiang Pan Tsinghua University
• Bin Wang Qihoo 360 AI Research

Keywords

No keywords are indexed for this paper.