A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection Article Swipe

PDF

Zhenshan Tan , Cheng Chen , Keyu Wen , Yuzhuo Qin , Xiaodong Gu ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2208.06615

Co-saliency detection (CoSOD) aims at discovering the repetitive salient objects from multiple images. Two primary challenges are group semantics extraction and noise object suppression. In this paper, we present a unified Two-stage grOup semantics PropagatIon and Contrastive learning NETwork (TopicNet) for CoSOD. TopicNet can be decomposed into two substructures, including a two-stage group semantics propagation module (TGSP) to address the first challenge and a contrastive learning module (CLM) to address the second challenge. Concretely, for TGSP, we design an image-to-group propagation module (IGP) to capture the consensus representation of intra-group similar features and a group-to-pixel propagation module (GPP) to build the relevancy of consensus representation. For CLM, with the design of positive samples, the semantic consistency is enhanced. With the design of negative samples, the noise objects are suppressed. Experimental results on three prevailing benchmarks reveal that TopicNet outperforms other competitors in terms of various evaluation metrics.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Computer science Semantics (computer science) Consistency (knowledge bases) Natural language processing Artificial intelligence Representation (politics) Stage (stratigraphy) Object (grammar) Group (periodic table) Noise (video) Feature learning Pattern recognition (psychology) Image (mathematics) Programming language Organic chemistry Political science Paleontology Law Biology Chemistry Politics

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2208.06615
PDF: https://arxiv.org/pdf/2208.06615
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4292107141

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4292107141

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2208.06615

Digital Object Identifier
Title: A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2022

Year of publication
Publication date: 2022-08-13

Full publication date if available
Authors: Zhenshan Tan, Cheng Chen, Keyu Wen, Yuzhuo Qin, Xiaodong Gu

List of authors in order
Landing page: https://arxiv.org/abs/2208.06615

Publisher landing page
PDF URL: https://arxiv.org/pdf/2208.06615

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/2208.06615

Direct OA link when available
Concepts: Computer science, Semantics (computer science), Consistency (knowledge bases), Natural language processing, Artificial intelligence, Representation (politics), Stage (stratigraphy), Object (grammar), Group (periodic table), Noise (video), Feature learning, Pattern recognition (psychology), Image (mathematics), Programming language, Organic chemistry, Political science, Paleontology, Law, Biology, Chemistry, Politics

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4292107141
doi	https://doi.org/10.48550/arxiv.2208.06615
ids.doi	https://doi.org/10.48550/arxiv.2208.06615
ids.openalex	https://openalex.org/W4292107141
fwci
type	preprint
title	A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11605
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9998000264167786
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Visual Attention and Saliency Detection
topics[1].id	https://openalex.org/T12650
topics[1].field.id	https://openalex.org/fields/28
topics[1].field.display_name	Neuroscience
topics[1].score	0.9527999758720398
topics[1].domain.id	https://openalex.org/domains/1
topics[1].domain.display_name	Life Sciences
topics[1].subfield.id	https://openalex.org/subfields/2805
topics[1].subfield.display_name	Cognitive Neuroscience
topics[1].display_name	Aesthetic Perception and Analysis
topics[2].id	https://openalex.org/T10971
topics[2].field.id	https://openalex.org/fields/28
topics[2].field.display_name	Neuroscience
topics[2].score	0.9103999733924866
topics[2].domain.id	https://openalex.org/domains/1
topics[2].domain.display_name	Life Sciences
topics[2].subfield.id	https://openalex.org/subfields/2809
topics[2].subfield.display_name	Sensory Systems
topics[2].display_name	Olfactory and Sensory Function Studies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.7334048748016357
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C184337299
concepts[1].level	2
concepts[1].score	0.6377394199371338
concepts[1].wikidata	https://www.wikidata.org/wiki/Q1437428
concepts[1].display_name	Semantics (computer science)
concepts[2].id	https://openalex.org/C2776436953
concepts[2].level	2
concepts[2].score	0.5800730586051941
concepts[2].wikidata	https://www.wikidata.org/wiki/Q5163215
concepts[2].display_name	Consistency (knowledge bases)
concepts[3].id	https://openalex.org/C204321447
concepts[3].level	1
concepts[3].score	0.5692267417907715
concepts[3].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[3].display_name	Natural language processing
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.5560520887374878
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C2776359362
concepts[5].level	3
concepts[5].score	0.553482174873352
concepts[5].wikidata	https://www.wikidata.org/wiki/Q2145286
concepts[5].display_name	Representation (politics)
concepts[6].id	https://openalex.org/C146357865
concepts[6].level	2
concepts[6].score	0.5078709721565247
concepts[6].wikidata	https://www.wikidata.org/wiki/Q1123245
concepts[6].display_name	Stage (stratigraphy)
concepts[7].id	https://openalex.org/C2781238097
concepts[7].level	2
concepts[7].score	0.4980742931365967
concepts[7].wikidata	https://www.wikidata.org/wiki/Q175026
concepts[7].display_name	Object (grammar)
concepts[8].id	https://openalex.org/C2781311116
concepts[8].level	2
concepts[8].score	0.4454529881477356
concepts[8].wikidata	https://www.wikidata.org/wiki/Q83306
concepts[8].display_name	Group (periodic table)
concepts[9].id	https://openalex.org/C99498987
concepts[9].level	3
concepts[9].score	0.42044156789779663
concepts[9].wikidata	https://www.wikidata.org/wiki/Q2210247
concepts[9].display_name	Noise (video)
concepts[10].id	https://openalex.org/C59404180
concepts[10].level	2
concepts[10].score	0.4129462242126465
concepts[10].wikidata	https://www.wikidata.org/wiki/Q17013334
concepts[10].display_name	Feature learning
concepts[11].id	https://openalex.org/C153180895
concepts[11].level	2
concepts[11].score	0.3862103521823883
concepts[11].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[11].display_name	Pattern recognition (psychology)
concepts[12].id	https://openalex.org/C115961682
concepts[12].level	2
concepts[12].score	0.3614693284034729
concepts[12].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[12].display_name	Image (mathematics)
concepts[13].id	https://openalex.org/C199360897
concepts[13].level	1
concepts[13].score	0.14503762125968933
concepts[13].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[13].display_name	Programming language
concepts[14].id	https://openalex.org/C178790620
concepts[14].level	1
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q11351
concepts[14].display_name	Organic chemistry
concepts[15].id	https://openalex.org/C17744445
concepts[15].level	0
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[15].display_name	Political science
concepts[16].id	https://openalex.org/C151730666
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q7205
concepts[16].display_name	Paleontology
concepts[17].id	https://openalex.org/C199539241
concepts[17].level	1
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[17].display_name	Law
concepts[18].id	https://openalex.org/C86803240
concepts[18].level	0
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q420
concepts[18].display_name	Biology
concepts[19].id	https://openalex.org/C185592680
concepts[19].level	0
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[19].display_name	Chemistry
concepts[20].id	https://openalex.org/C94625758
concepts[20].level	2
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q7163
concepts[20].display_name	Politics
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.7334048748016357
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/semantics
keywords[1].score	0.6377394199371338
keywords[1].display_name	Semantics (computer science)
keywords[2].id	https://openalex.org/keywords/consistency
keywords[2].score	0.5800730586051941
keywords[2].display_name	Consistency (knowledge bases)
keywords[3].id	https://openalex.org/keywords/natural-language-processing
keywords[3].score	0.5692267417907715
keywords[3].display_name	Natural language processing
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.5560520887374878
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/representation
keywords[5].score	0.553482174873352
keywords[5].display_name	Representation (politics)
keywords[6].id	https://openalex.org/keywords/stage
keywords[6].score	0.5078709721565247
keywords[6].display_name	Stage (stratigraphy)
keywords[7].id	https://openalex.org/keywords/object
keywords[7].score	0.4980742931365967
keywords[7].display_name	Object (grammar)
keywords[8].id	https://openalex.org/keywords/group
keywords[8].score	0.4454529881477356
keywords[8].display_name	Group (periodic table)
keywords[9].id	https://openalex.org/keywords/noise
keywords[9].score	0.42044156789779663
keywords[9].display_name	Noise (video)
keywords[10].id	https://openalex.org/keywords/feature-learning
keywords[10].score	0.4129462242126465
keywords[10].display_name	Feature learning
keywords[11].id	https://openalex.org/keywords/pattern-recognition
keywords[11].score	0.3862103521823883
keywords[11].display_name	Pattern recognition (psychology)
keywords[12].id	https://openalex.org/keywords/image
keywords[12].score	0.3614693284034729
keywords[12].display_name	Image (mathematics)
keywords[13].id	https://openalex.org/keywords/programming-language
keywords[13].score	0.14503762125968933
keywords[13].display_name	Programming language
language	en
locations[0].id	pmh:oai:arXiv.org:2208.06615
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/2208.06615
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/2208.06615
locations[1].id	doi:10.48550/arxiv.2208.06615
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.2208.06615
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5064787764
authorships[0].author.orcid	https://orcid.org/0000-0003-3466-5417
authorships[0].author.display_name	Zhenshan Tan
authorships[0].author_position	first
authorships[0].raw_author_name	Tan, Zhenshan
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100420548
authorships[1].author.orcid	https://orcid.org/0000-0002-4203-2145
authorships[1].author.display_name	Cheng Chen
authorships[1].author_position	middle
authorships[1].raw_author_name	Chen, Cheng
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5004061050
authorships[2].author.orcid	https://orcid.org/0000-0002-5048-9014
authorships[2].author.display_name	Keyu Wen
authorships[2].author_position	middle
authorships[2].raw_author_name	Wen, Keyu
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5033550999
authorships[3].author.orcid	https://orcid.org/0000-0002-7738-3180
authorships[3].author.display_name	Yuzhuo Qin
authorships[3].author_position	middle
authorships[3].raw_author_name	Qin, Yuzhuo
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5101294804
authorships[4].author.orcid
authorships[4].author.display_name	Xiaodong Gu
authorships[4].author_position	last
authorships[4].raw_author_name	Gu, Xiaodong
authorships[4].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/2208.06615
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11605
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9998000264167786
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Visual Attention and Saliency Detection
related_works	https://openalex.org/W2503350049, https://openalex.org/W2329386257, https://openalex.org/W2397616145, https://openalex.org/W2397320258, https://openalex.org/W1603736412, https://openalex.org/W4324058133, https://openalex.org/W648618910, https://openalex.org/W4393624937, https://openalex.org/W4323929292, https://openalex.org/W4390871823
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2208.06615
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/2208.06615
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/2208.06615
primary_location.id	pmh:oai:arXiv.org:2208.06615
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/2208.06615
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/2208.06615
publication_date	2022-08-13
publication_year	2022
referenced_works_count	0
abstract_inverted_index.a	29, 50, 63, 93
abstract_inverted_index.In	24
abstract_inverted_index.an	78
abstract_inverted_index.at	4
abstract_inverted_index.be	44
abstract_inverted_index.in	141
abstract_inverted_index.is	116
abstract_inverted_index.of	88, 102, 110, 121, 143
abstract_inverted_index.on	131
abstract_inverted_index.to	57, 68, 83, 98
abstract_inverted_index.we	27, 76
abstract_inverted_index.For	105
abstract_inverted_index.Two	13
abstract_inverted_index.and	20, 35, 62, 92
abstract_inverted_index.are	16, 127
abstract_inverted_index.can	43
abstract_inverted_index.for	40, 74
abstract_inverted_index.the	6, 59, 70, 85, 100, 108, 113, 119, 124
abstract_inverted_index.two	47
abstract_inverted_index.CLM,	106
abstract_inverted_index.With	118
abstract_inverted_index.aims	3
abstract_inverted_index.from	10
abstract_inverted_index.into	46
abstract_inverted_index.that	136
abstract_inverted_index.this	25
abstract_inverted_index.with	107
abstract_inverted_index.(CLM)	67
abstract_inverted_index.(GPP)	97
abstract_inverted_index.(IGP)	82
abstract_inverted_index.TGSP,	75
abstract_inverted_index.build	99
abstract_inverted_index.first	60
abstract_inverted_index.grOup	32
abstract_inverted_index.group	17, 52
abstract_inverted_index.noise	21, 125
abstract_inverted_index.other	139
abstract_inverted_index.terms	142
abstract_inverted_index.three	132
abstract_inverted_index.(TGSP)	56
abstract_inverted_index.CoSOD.	41
abstract_inverted_index.design	77, 109, 120
abstract_inverted_index.module	55, 66, 81, 96
abstract_inverted_index.object	22
abstract_inverted_index.paper,	26
abstract_inverted_index.reveal	135
abstract_inverted_index.second	71
abstract_inverted_index.(CoSOD)	2
abstract_inverted_index.NETwork	38
abstract_inverted_index.address	58, 69
abstract_inverted_index.capture	84
abstract_inverted_index.images.	12
abstract_inverted_index.objects	9, 126
abstract_inverted_index.present	28
abstract_inverted_index.primary	14
abstract_inverted_index.results	130
abstract_inverted_index.salient	8
abstract_inverted_index.similar	90
abstract_inverted_index.unified	30
abstract_inverted_index.various	144
abstract_inverted_index.TopicNet	42, 137
abstract_inverted_index.features	91
abstract_inverted_index.learning	37, 65
abstract_inverted_index.metrics.	146
abstract_inverted_index.multiple	11
abstract_inverted_index.negative	122
abstract_inverted_index.positive	111
abstract_inverted_index.samples,	112, 123
abstract_inverted_index.semantic	114
abstract_inverted_index.Two-stage	31
abstract_inverted_index.challenge	61
abstract_inverted_index.consensus	86, 103
abstract_inverted_index.detection	1
abstract_inverted_index.enhanced.	117
abstract_inverted_index.including	49
abstract_inverted_index.relevancy	101
abstract_inverted_index.semantics	18, 33, 53
abstract_inverted_index.two-stage	51
abstract_inverted_index.(TopicNet)	39
abstract_inverted_index.benchmarks	134
abstract_inverted_index.challenge.	72
abstract_inverted_index.challenges	15
abstract_inverted_index.decomposed	45
abstract_inverted_index.evaluation	145
abstract_inverted_index.extraction	19
abstract_inverted_index.prevailing	133
abstract_inverted_index.repetitive	7
abstract_inverted_index.Co-saliency	0
abstract_inverted_index.Concretely,	73
abstract_inverted_index.Contrastive	36
abstract_inverted_index.PropagatIon	34
abstract_inverted_index.competitors	140
abstract_inverted_index.consistency	115
abstract_inverted_index.contrastive	64
abstract_inverted_index.discovering	5
abstract_inverted_index.intra-group	89
abstract_inverted_index.outperforms	138
abstract_inverted_index.propagation	54, 80, 95
abstract_inverted_index.suppressed.	128
abstract_inverted_index.Experimental	129
abstract_inverted_index.suppression.	23
abstract_inverted_index.group-to-pixel	94
abstract_inverted_index.image-to-group	79
abstract_inverted_index.representation	87
abstract_inverted_index.substructures,	48
abstract_inverted_index.representation.	104
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile