Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations
This work addresses the need for more efficient annotation methods in object detection, particularly for applications requiring reduced labeling costs, though it is incremental in building on existing semi-supervised techniques.
The paper tackles the problem of weakly semi-supervised object detection using cheap point annotations instead of bounding boxes, achieving improved performance as demonstrated in experiments on multiple datasets and data regimes.
Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we present Point-Teaching, a weakly semi-supervised object detection framework to fully exploit the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes.