# Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Source: [Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images](<https://www.sota2.com/research/paper/68fa69b51e209131cea239dc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-24T15:25:58.258Z

Authors: Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding, Longjin Ran, Xiaoxin Chen, Wenyu Liu

Published: 2021-04-04T03:01:52.000Z

## Abstract

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using $7991$ salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at \\url{https://github.com/hustvl/BoxCaseg}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Instance Segmentation on COCO 2017 (test-dev)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-2017-test-dev.md>): Instance Segmentation; COCO 2017 (test-dev); AP (Overall): 30.9.

- [Instance Segmentation on COCO (test-dev)](<https://www.sota2.com/research/sota/instance-segmentation-on-coco-test-dev.md>): Instance Segmentation; COCO (test-dev); APM: 32.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.01526>)

[PDF](<https://arxiv.org/pdf/2104.01526.pdf>)

[Implementation](<https://github.com/hustvl/BoxCaseg>)