Box-supervised Instance Segmentation
13 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
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
yangxue0827/h2rbox-mmrotate
•
•
Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection.
BoxInst: High-Performance Instance Segmentation with Box Annotations
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training.
Box-supervised Instance Segmentation with Level Set Evolution
A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance.
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention.
Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior
chengchunhsu/WSIS_BBTP
•
•
NeurIPS 2019
This paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object.
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
zbf1991/A2GNN
•
•
More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset.
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation
hustvl/boxteacher
•
•
CVPR 2023
Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes.
SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation
Weakly supervised instance segmentation using only bounding box annotations has recently attracted much research attention.
