Semantic Segmentation with Scarce Data
This addresses the high cost of fine annotations in vision tasks, offering a practical solution for domains with limited labeled data, though it is incremental in combining existing supervision types.
The paper tackles the problem of semantic segmentation with scarce data by leveraging coarsely annotated data alongside fine supervision, achieving a 15.52% mIoU improvement over training only on fine data and a 5.28% mIoU gain over using coarse masks alone.
Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative as it is usually substantially more cheap. In this work, we present a method to leverage coarsely annotated data along with fine supervision to produce better segmentation results than would be obtained when training using only the fine data. We validate our approach by simulating a scarce data setting with less than 200 low resolution images from the Cityscapes dataset and show that our method substantially outperforms solely training on the fine annotation data by an average of 15.52% mIoU and outperforms the coarse mask by an average of 5.28% mIoU.