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

PDF

Jinxiang Lai , Jiawei Zhan , Jian Li , Binbin Gao , Jun Liu , Song Guo ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2504.05137

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.

Related Topics

Truth And Reconciliation Commission Of Canada

Alanis Morissette

2025 Nba Draft

28 Years Later

Reich Ministry Of Public Enlightenment And Propaganda

Mahmood Mamdani

Rick Hurst

Mutual Aid

Degenerate Art Exhibition

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2504.05137
PDF: https://arxiv.org/pdf/2504.05137
OA Status: green
OpenAlex ID: https://openalex.org/W4416118728

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416118728

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2504.05137

Digital Object Identifier
Title: BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-04-07

Full publication date if available
Authors: Jinxiang Lai, Jiawei Zhan, Jian Li, Binbin Gao, Jun Liu, Song Guo

List of authors in order
Landing page: https://arxiv.org/abs/2504.05137

Publisher landing page
PDF URL: https://arxiv.org/pdf/2504.05137

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2504.05137

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416118728
doi	https://doi.org/10.48550/arxiv.2504.05137
ids.doi	https://doi.org/10.48550/arxiv.2504.05137
ids.openalex	https://openalex.org/W4416118728
fwci
type	preprint
title	BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2504.05137
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license	cc-by-nc-sa
locations[0].pdf_url	https://arxiv.org/pdf/2504.05137
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id	https://openalex.org/licenses/cc-by-nc-sa
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2504.05137
locations[1].id	doi:10.48550/arxiv.2504.05137
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2504.05137
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5111101973
authorships[0].author.orcid
authorships[0].author.display_name	Jinxiang Lai
authorships[0].author_position	first
authorships[0].raw_author_name	Lai, Jinxiang
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5021903335
authorships[1].author.orcid
authorships[1].author.display_name	Jiawei Zhan
authorships[1].author_position	middle
authorships[1].raw_author_name	Zhan, Jiawei
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100402515
authorships[2].author.orcid	https://orcid.org/0000-0002-5749-2734
authorships[2].author.display_name	Jian Li
authorships[2].author_position	middle
authorships[2].raw_author_name	Li, Jian
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5110532661
authorships[3].author.orcid
authorships[3].author.display_name	Binbin Gao
authorships[3].author_position	middle
authorships[3].raw_author_name	Gao, Bin-Bin
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100716276
authorships[4].author.orcid	https://orcid.org/0000-0002-3228-7443
authorships[4].author.display_name	Jun Liu
authorships[4].author_position	last
authorships[4].raw_author_name	Liu, Jun
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5043464306
authorships[5].author.orcid	https://orcid.org/0000-0001-9831-2202
authorships[5].author.display_name	Song Guo
authorships[5].author_position	middle
authorships[5].raw_author_name	Guo, Song
authorships[5].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2504.05137
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
has_fulltext	True
is_retracted	False
updated_date	2025-11-28T05:34:32.304445
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2504.05137
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license	cc-by-nc-sa
best_oa_location.pdf_url	https://arxiv.org/pdf/2504.05137
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id	https://openalex.org/licenses/cc-by-nc-sa
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2504.05137
primary_location.id	pmh:oai:arXiv.org:2504.05137
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license	cc-by-nc-sa
primary_location.pdf_url	https://arxiv.org/pdf/2504.05137
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id	https://openalex.org/licenses/cc-by-nc-sa
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2504.05137
publication_date	2025-04-07
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	34
abstract_inverted_index.PC	81, 112, 133
abstract_inverted_index.be	135
abstract_inverted_index.by	73
abstract_inverted_index.of	19, 70, 90, 97, 121
abstract_inverted_index.to	5, 65, 85, 137
abstract_inverted_index.we	32
abstract_inverted_index.QAM	54, 110, 131
abstract_inverted_index.The	53, 80
abstract_inverted_index.aim	4
abstract_inverted_index.and	40, 48, 59, 104, 111, 128, 132
abstract_inverted_index.are	113
abstract_inverted_index.box	11
abstract_inverted_index.can	134
abstract_inverted_index.our	122
abstract_inverted_index.the	17, 25, 44, 49, 62, 68, 75, 88, 91, 95, 98, 108, 119, 125, 130
abstract_inverted_index.two	38
abstract_inverted_index.have	15
abstract_inverted_index.help	66
abstract_inverted_index.mask	63
abstract_inverted_index.only	10
abstract_inverted_index.over	124
abstract_inverted_index.show	118
abstract_inverted_index.this	30
abstract_inverted_index.upon	29
abstract_inverted_index.with	9, 94
abstract_inverted_index.(PC).	52
abstract_inverted_index.(QAM)	47
abstract_inverted_index.masks	23, 58, 93
abstract_inverted_index.named	43
abstract_inverted_index.noisy	71
abstract_inverted_index.novel	39
abstract_inverted_index.other	139
abstract_inverted_index.under	24
abstract_inverted_index.BoxSeg	35, 123
abstract_inverted_index.Module	46
abstract_inverted_index.Recent	13
abstract_inverted_index.better	60
abstract_inverted_index.effect	69
abstract_inverted_index.masks,	72
abstract_inverted_index.masks.	102
abstract_inverted_index.pseudo	22, 57, 101
abstract_inverted_index.reduce	67
abstract_inverted_index.achieve	6
abstract_inverted_index.applied	136
abstract_inverted_index.further	86
abstract_inverted_index.general	41
abstract_inverted_index.improve	87, 138
abstract_inverted_index.methods	3, 14
abstract_inverted_index.models.	140
abstract_inverted_index.modules	42
abstract_inverted_index.obtains	55
abstract_inverted_index.propose	33
abstract_inverted_index.quality	64, 89
abstract_inverted_index.results	117
abstract_inverted_index.Building	28
abstract_inverted_index.Learning	84
abstract_inverted_index.analyses	106
abstract_inverted_index.guidance	96
abstract_inverted_index.imitates	82
abstract_inverted_index.instance	1, 7
abstract_inverted_index.measures	61
abstract_inverted_index.methods,	127
abstract_inverted_index.obtained	99
abstract_inverted_index.proposed	109
abstract_inverted_index.Extensive	115
abstract_inverted_index.acquiring	20
abstract_inverted_index.framework	36
abstract_inverted_index.involving	37
abstract_inverted_index.Copy-paste	51
abstract_inverted_index.effective.	114
abstract_inverted_index.framework.	27
abstract_inverted_index.illustrate	129
abstract_inverted_index.leveraging	74
abstract_inverted_index.mechanism.	79
abstract_inverted_index.multi-mask	77
abstract_inverted_index.Theoretical	103
abstract_inverted_index.demonstrate	107
abstract_inverted_index.foundation,	31
abstract_inverted_index.low-quality	92
abstract_inverted_index.superiority	120
abstract_inverted_index.annotations.	12
abstract_inverted_index.demonstrated	16
abstract_inverted_index.experimental	105, 116
abstract_inverted_index.high-quality	21, 56, 100
abstract_inverted_index.segmentation	2, 8
abstract_inverted_index.Peer-Assisted	83
abstract_inverted_index.Peer-assisted	50
abstract_inverted_index.Quality-Aware	45
abstract_inverted_index.effectiveness	18
abstract_inverted_index.quality-aware	76
abstract_inverted_index.Box-supervised	0
abstract_inverted_index.complementation	78
abstract_inverted_index.teacher-student	26
abstract_inverted_index.state-of-the-art	126
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile