Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Bowen Cheng, Omkar Parkhi, Alexander Kirillov• 2021

Related benchmarks

TaskDatasetResultRank
Instance SegmentationCOCO 2017 (val)
APm0.435
1144
Multi-organ SegmentationSynapse multi-organ CT v1 (fixed (18 train, 12 test))
DSC0.7192
16
Liver SegmentationMulti-phasic MRI (test)
DSC88.72
16
Image SegmentationKvasir-SEG (train)
Dice Score73.05
7
Image SegmentationProstate
Dice Score0.7346
7
Showing 5 of 5 rows

Other info

Code

Follow for update