Box-supervised Instance Segmentation
12 papers with code • 2 benchmarks • 1 datasets
This task aims to achieve instance segmentation with weakly bounding box annotations.
Benchmarks
These leaderboards are used to track progress in Box-supervised Instance Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
MS COCO
Most implemented papers
BoxSnake: Polygonal Instance Segmentation with Box Supervision
yangr116/boxsnake
•
•
ICCV 2023
Box-supervised instance segmentation has gained much attention as it requires only simple box annotations instead of costly mask or polygon annotations.
Label-efficient Segmentation via Affinity Propagation
circleradon/apro
•
•
NeurIPS 2023
In this work, we formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels.
