Mask R-CNN Article Swipe

PDF

Kaiming He , Georgia Gkioxari , Piotr Dollár , Ross Girshick ·

YOU? · · 2017 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1703.06870

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/facebookresearch/Detectron

Related Topics

History

Concepts

History

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/1703.06870
PDF: https://arxiv.org/pdf/1703.06870
OA Status: green
Cited By: 378
Related Works: 10
OpenAlex ID: https://openalex.org/W4394669457

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4394669457

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.1703.06870

Digital Object Identifier
Title: Mask R-CNN

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2017

Year of publication
Publication date: 2017-03-20

Full publication date if available
Authors: Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick

List of authors in order
Landing page: https://arxiv.org/abs/1703.06870

Publisher landing page
PDF URL: https://arxiv.org/pdf/1703.06870

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/1703.06870

Direct OA link when available
Concepts: History

Top concepts (fields/topics) attached by OpenAlex
Cited by: 378

Total citation count in OpenAlex
Citations by year (recent): 2025: 50, 2024: 80, 2023: 106, 2022: 54, 2021: 34

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4394669457
doi	https://doi.org/10.48550/arxiv.1703.06870
ids.doi	https://doi.org/10.48550/arxiv.1703.06870
ids.openalex	https://openalex.org/W4394669457
fwci
type	preprint
title	Mask R-CNN
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C95457728
concepts[0].level	0
concepts[0].score	0.3508146405220032
concepts[0].wikidata	https://www.wikidata.org/wiki/Q309
concepts[0].display_name	History
keywords[0].id	https://openalex.org/keywords/history
keywords[0].score	0.3508146405220032
keywords[0].display_name	History
language	en
locations[0].id	pmh:oai:arXiv.org:1703.06870
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
locations[0].pdf_url	https://arxiv.org/pdf/1703.06870
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/1703.06870
locations[1].id	doi:10.48550/arxiv.1703.06870
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.1703.06870
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5100700361
authorships[0].author.orcid	https://orcid.org/0000-0001-7318-9658
authorships[0].author.display_name	Kaiming He
authorships[0].author_position	first
authorships[0].raw_author_name	Kaiming He
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5014407395
authorships[1].author.orcid
authorships[1].author.display_name	Georgia Gkioxari
authorships[1].author_position	middle
authorships[1].raw_author_name	Georgia Gkioxari
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5057866698
authorships[2].author.orcid
authorships[2].author.display_name	Piotr Dollár
authorships[2].author_position	middle
authorships[2].raw_author_name	Piotr Dollár
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5049246408
authorships[3].author.orcid
authorships[3].author.display_name	Ross Girshick
authorships[3].author_position	last
authorships[3].raw_author_name	Ross Girshick
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/1703.06870
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-04-11T00:00:00
display_name	Mask R-CNN
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic
related_works	https://openalex.org/W2503791906, https://openalex.org/W2332941581, https://openalex.org/W2325454561, https://openalex.org/W2203829371, https://openalex.org/W2587645680, https://openalex.org/W2219051300, https://openalex.org/W2486751915, https://openalex.org/W2510471065, https://openalex.org/W2736167416, https://openalex.org/W2317964688
cited_by_count	378
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	50
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	80
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	106
counts_by_year[3].year	2022
counts_by_year[3].cited_by_count	54
counts_by_year[4].year	2021
counts_by_year[4].cited_by_count	34
counts_by_year[5].year	2020
counts_by_year[5].cited_by_count	21
counts_by_year[6].year	2019
counts_by_year[6].cited_by_count	18
counts_by_year[7].year	2018
counts_by_year[7].cited_by_count	13
counts_by_year[8].year	2017
counts_by_year[8].cited_by_count	2
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:1703.06870
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
best_oa_location.pdf_url	https://arxiv.org/pdf/1703.06870
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
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/1703.06870
primary_location.id	pmh:oai:arXiv.org:1703.06870
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
primary_location.pdf_url	https://arxiv.org/pdf/1703.06870
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/1703.06870
publication_date	2017-03-20
publication_year	2017
referenced_works_count	0
abstract_inverted_index.5	75
abstract_inverted_index.a	2, 24, 41, 67, 152
abstract_inverted_index.We	0, 98, 142
abstract_inverted_index.an	19, 45
abstract_inverted_index.as	151
abstract_inverted_index.at	74
abstract_inverted_index.by	39
abstract_inverted_index.in	18, 48, 94, 102, 160
abstract_inverted_index.is	60, 80
abstract_inverted_index.of	106, 110
abstract_inverted_index.on	133
abstract_inverted_index.to	62, 70, 82, 84, 90
abstract_inverted_index.us	89
abstract_inverted_index.Our	13
abstract_inverted_index.The	31
abstract_inverted_index.all	103, 129
abstract_inverted_index.and	6, 64, 118, 124, 146, 155
abstract_inverted_index.at:	168
abstract_inverted_index.box	56
abstract_inverted_index.for	9, 28, 43, 54
abstract_inverted_index.has	164
abstract_inverted_index.our	144
abstract_inverted_index.the	51, 95, 107, 137
abstract_inverted_index.top	100
abstract_inverted_index.2016	139
abstract_inverted_index.COCO	108, 138
abstract_inverted_index.Code	163
abstract_inverted_index.Mask	34, 58, 78, 126
abstract_inverted_index.adds	65
abstract_inverted_index.been	165
abstract_inverted_index.each	29
abstract_inverted_index.ease	157
abstract_inverted_index.easy	81
abstract_inverted_index.fps.	76
abstract_inverted_index.help	156
abstract_inverted_index.hope	143
abstract_inverted_index.made	166
abstract_inverted_index.mask	27, 47
abstract_inverted_index.only	66
abstract_inverted_index.same	96
abstract_inverted_index.show	99
abstract_inverted_index.will	149
abstract_inverted_index.with	50
abstract_inverted_index.R-CNN	38, 59, 79, 127
abstract_inverted_index.bells	123
abstract_inverted_index.e.g.,	87
abstract_inverted_index.every	134
abstract_inverted_index.human	92
abstract_inverted_index.image	20
abstract_inverted_index.other	85
abstract_inverted_index.poses	93
abstract_inverted_index.serve	150
abstract_inverted_index.small	68
abstract_inverted_index.solid	153
abstract_inverted_index.suite	109
abstract_inverted_index.task,	135
abstract_inverted_index.three	104
abstract_inverted_index.train	63
abstract_inverted_index.while	21
abstract_inverted_index.Faster	37, 71
abstract_inverted_index.R-CNN,	35, 72
abstract_inverted_index.adding	40
abstract_inverted_index.branch	42, 53
abstract_inverted_index.called	33
abstract_inverted_index.future	158
abstract_inverted_index.object	10, 46, 116
abstract_inverted_index.person	119
abstract_inverted_index.simple	61, 145
abstract_inverted_index.tasks,	86
abstract_inverted_index.tracks	105
abstract_inverted_index.Without	122
abstract_inverted_index.detects	16
abstract_inverted_index.entries	132
abstract_inverted_index.extends	36
abstract_inverted_index.general	7
abstract_inverted_index.method,	32
abstract_inverted_index.objects	17
abstract_inverted_index.present	1
abstract_inverted_index.results	101
abstract_inverted_index.running	73
abstract_inverted_index.simple,	4
abstract_inverted_index.allowing	88
abstract_inverted_index.approach	14, 148
abstract_inverted_index.baseline	154
abstract_inverted_index.bounding	55
abstract_inverted_index.estimate	91
abstract_inverted_index.existing	52
abstract_inverted_index.instance	11, 113
abstract_inverted_index.keypoint	120
abstract_inverted_index.overhead	69
abstract_inverted_index.parallel	49
abstract_inverted_index.research	159
abstract_inverted_index.winners.	141
abstract_inverted_index.Moreover,	77
abstract_inverted_index.available	167
abstract_inverted_index.challenge	140
abstract_inverted_index.effective	147
abstract_inverted_index.existing,	130
abstract_inverted_index.flexible,	5
abstract_inverted_index.framework	8
abstract_inverted_index.including	112, 136
abstract_inverted_index.instance.	30
abstract_inverted_index.whistles,	125
abstract_inverted_index.detection,	117
abstract_inverted_index.detection.	121
abstract_inverted_index.framework.	97
abstract_inverted_index.generalize	83
abstract_inverted_index.generating	23
abstract_inverted_index.predicting	44
abstract_inverted_index.challenges,	111
abstract_inverted_index.efficiently	15
abstract_inverted_index.outperforms	128
abstract_inverted_index.bounding-box	115
abstract_inverted_index.conceptually	3
abstract_inverted_index.high-quality	25
abstract_inverted_index.recognition.	57, 162
abstract_inverted_index.segmentation	26
abstract_inverted_index.single-model	131
abstract_inverted_index.segmentation,	114
abstract_inverted_index.segmentation.	12
abstract_inverted_index.instance-level	161
abstract_inverted_index.simultaneously	22
abstract_inverted_index.https://github.com/facebookresearch/Detectron	169
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile