BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lai, Jinxiang, Wu, Wenlong, Zhan, Jiawei, Li, Jian, Gao, Bin-Bin, Liu, Jun, Zhang, Jie, Guo, Song
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912313530908672
author Lai, Jinxiang
Wu, Wenlong
Zhan, Jiawei
Li, Jian
Gao, Bin-Bin
Liu, Jun
Zhang, Jie
Guo, Song
author_facet Lai, Jinxiang
Wu, Wenlong
Zhan, Jiawei
Li, Jian
Gao, Bin-Bin
Liu, Jun
Zhang, Jie
Guo, Song
contents Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations. Recent methods have demonstrated the effectiveness of acquiring high-quality pseudo masks under the teacher-student framework. Building upon this foundation, we propose a BoxSeg framework involving two novel and general modules named the Quality-Aware Module (QAM) and the Peer-assisted Copy-paste (PC). The QAM obtains high-quality pseudo masks and better measures the mask quality to help reduce the effect of noisy masks, by leveraging the quality-aware multi-mask complementation mechanism. The PC imitates Peer-Assisted Learning to further improve the quality of the low-quality masks with the guidance of the obtained high-quality pseudo masks. Theoretical and experimental analyses demonstrate the proposed QAM and PC are effective. Extensive experimental results show the superiority of our BoxSeg over the state-of-the-art methods, and illustrate the QAM and PC can be applied to improve other models.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
Lai, Jinxiang
Wu, Wenlong
Zhan, Jiawei
Li, Jian
Gao, Bin-Bin
Liu, Jun
Zhang, Jie
Guo, Song
Computer Vision and Pattern Recognition
Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations. Recent methods have demonstrated the effectiveness of acquiring high-quality pseudo masks under the teacher-student framework. Building upon this foundation, we propose a BoxSeg framework involving two novel and general modules named the Quality-Aware Module (QAM) and the Peer-assisted Copy-paste (PC). The QAM obtains high-quality pseudo masks and better measures the mask quality to help reduce the effect of noisy masks, by leveraging the quality-aware multi-mask complementation mechanism. The PC imitates Peer-Assisted Learning to further improve the quality of the low-quality masks with the guidance of the obtained high-quality pseudo masks. Theoretical and experimental analyses demonstrate the proposed QAM and PC are effective. Extensive experimental results show the superiority of our BoxSeg over the state-of-the-art methods, and illustrate the QAM and PC can be applied to improve other models.
title BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05137