S4OD: Semi-Supervised learning for Single-Stage Object Detection
This addresses the challenge of applying semi-supervised learning to single-stage detectors, which is incremental as it adapts existing strategies to a specific bottleneck.
The paper tackles the problem of class imbalance in semi-supervised single-stage object detectors by proposing a dynamic self-adaptive threshold strategy and a regression uncertainty module, achieving 35.0% AP on FCOS and 32.9% on RetinaNet with only 10% labeled COCO data.
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting high-quality pseudo labels based on classification scores. However, directly applying this strategy to single-stage detectors would aggravate the class imbalance with fewer positive samples. Thus, single-stage detectors have to consider both quality and quantity of pseudo labels simultaneously. In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity. Besides, to assess the regression quality of pseudo labels in single-stage detectors, we propose a module to compute the regression uncertainty of boxes based on Non-Maximum Suppression. By leveraging only 10% labeled data from COCO, our method achieves 35.0% AP on anchor-free detector (FCOS) and 32.9% on anchor-based detector (RetinaNet).