Bounding Box Priors for Cell Detection with Point Annotations
This work addresses the challenge of reducing annotation costs for cell detection in medical imaging, though it is incremental as it builds on weakly semi-supervised learning methods.
The paper tackles the problem of cell detection in images with limited bounding box annotations by using a prior on cell size to replace point annotations with stochastic boxes during training, achieving a 5.56 mAP improvement over two-stage methods when only 5% of images are box-labelled.
The size of an individual cell type, such as a red blood cell, does not vary much among humans. We use this knowledge as a prior for classifying and detecting cells in images with only a few ground truth bounding box annotations, while most of the cells are annotated with points. This setting leads to weakly semi-supervised learning. We propose replacing points with either stochastic (ST) boxes or bounding box predictions during the training process. The proposed "mean-IOU" ST box maximizes the overlap with all the boxes belonging to the sample space with a class-specific approximated prior probability distribution of bounding boxes. Our method trains with both box- and point-labelled images in conjunction, unlike the existing methods, which train first with box- and then point-labelled images. In the most challenging setting, when only 5% images are box-labelled, quantitative experiments on a urine dataset show that our one-stage method outperforms two-stage methods by 5.56 mAP. Furthermore, we suggest an approach that partially answers "how many box-labelled annotations are necessary?" before training a machine learning model.