Pointly-Supervised Instance Segmentation
About
We propose an embarrassingly simple point annotation scheme to collect weak supervision for instance segmentation. In addition to bounding boxes, we collect binary labels for a set of points uniformly sampled inside each bounding box. We show that the existing instance segmentation models developed for full mask supervision can be seamlessly trained with point-based supervision collected via our scheme. Remarkably, Mask R-CNN trained on COCO, PASCAL VOC, Cityscapes, and LVIS with only 10 annotated random points per object achieves 94%--98% of its fully-supervised performance, setting a strong baseline for weakly-supervised instance segmentation. The new point annotation scheme is approximately 5 times faster than annotating full object masks, making high-quality instance segmentation more accessible in practice. Inspired by the point-based annotation form, we propose a modification to PointRend instance segmentation module. For each object, the new architecture, called Implicit PointRend, generates parameters for a function that makes the final point-level mask prediction. Implicit PointRend is more straightforward and uses a single point-level mask loss. Our experiments show that the new module is more suitable for the point-based supervision.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Instance Segmentation | COCO 2017 (val) | APm0.435 | 1144 | |
| Multi-organ Segmentation | Synapse multi-organ CT v1 (fixed (18 train, 12 test)) | DSC0.7192 | 16 | |
| Liver Segmentation | Multi-phasic MRI (test) | DSC88.72 | 16 | |
| Image Segmentation | Kvasir-SEG (train) | Dice Score73.05 | 7 | |
| Image Segmentation | Prostate | Dice Score0.7346 | 7 |