Region-Based Representations Revisited Article Swipe

PDF

Michal Shlapentokh-Rothman , Ansel Blume , Yao Xiao , Yuqun Wu , T V Sethuraman , Heyi Tao , Jae Yong Lee , Wilfredo Torres , Yu-Xiong Wang , Derek Hoiem ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2402.02352

We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.

Related Topics

Computer Science

Concepts

Computer science

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2402.02352
PDF: https://arxiv.org/pdf/2402.02352
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4391591033

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4391591033

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2402.02352

Digital Object Identifier
Title: Region-Based Representations Revisited

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-02-04

Full publication date if available
Authors: Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao, Yuqun Wu, T V Sethuraman, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem

List of authors in order
Landing page: https://arxiv.org/abs/2402.02352

Publisher landing page
PDF URL: https://arxiv.org/pdf/2402.02352

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/2402.02352

Direct OA link when available
Concepts: Computer science

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

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

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4391591033
doi	https://doi.org/10.48550/arxiv.2402.02352
ids.doi	https://doi.org/10.48550/arxiv.2402.02352
ids.openalex	https://openalex.org/W4391591033
fwci
type	preprint
title	Region-Based Representations Revisited
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.3714039921760559
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.3714039921760559
keywords[0].display_name	Computer science
language	en
locations[0].id	pmh:oai:arXiv.org:2402.02352
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
locations[0].pdf_url	https://arxiv.org/pdf/2402.02352
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2402.02352
locations[1].id	doi:10.48550/arxiv.2402.02352
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	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
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.2402.02352
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5020086880
authorships[0].author.orcid
authorships[0].author.display_name	Michal Shlapentokh-Rothman
authorships[0].author_position	first
authorships[0].raw_author_name	Shlapentokh-Rothman, Michal
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5093875985
authorships[1].author.orcid
authorships[1].author.display_name	Ansel Blume
authorships[1].author_position	middle
authorships[1].raw_author_name	Blume, Ansel
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102787930
authorships[2].author.orcid	https://orcid.org/0000-0003-2282-1785
authorships[2].author.display_name	Yao Xiao
authorships[2].author_position	middle
authorships[2].raw_author_name	Xiao, Yao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5007554120
authorships[3].author.orcid
authorships[3].author.display_name	Yuqun Wu
authorships[3].author_position	middle
authorships[3].raw_author_name	Wu, Yuqun
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5041130310
authorships[4].author.orcid	https://orcid.org/0009-0004-9246-8547
authorships[4].author.display_name	T V Sethuraman
authorships[4].author_position	middle
authorships[4].raw_author_name	T V, Sethuraman
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5066594399
authorships[5].author.orcid
authorships[5].author.display_name	Heyi Tao
authorships[5].author_position	middle
authorships[5].raw_author_name	Tao, Heyi
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5100369464
authorships[6].author.orcid	https://orcid.org/0000-0002-4967-911X
authorships[6].author.display_name	Jae Yong Lee
authorships[6].author_position	middle
authorships[6].raw_author_name	Lee, Jae Yong
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5082112345
authorships[7].author.orcid
authorships[7].author.display_name	Wilfredo Torres
authorships[7].author_position	middle
authorships[7].raw_author_name	Torres, Wilfredo
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5102952938
authorships[8].author.orcid
authorships[8].author.display_name	Yu-Xiong Wang
authorships[8].author_position	middle
authorships[8].raw_author_name	Wang, Yu-Xiong
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5009682734
authorships[9].author.orcid	https://orcid.org/0000-0001-6260-5708
authorships[9].author.display_name	Derek Hoiem
authorships[9].author_position	last
authorships[9].raw_author_name	Hoiem, Derek
authorships[9].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/2402.02352
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Region-Based Representations Revisited
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic
related_works	https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W2382290278, https://openalex.org/W2478288626, https://openalex.org/W2350741829, https://openalex.org/W2530322880, https://openalex.org/W1596801655
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2402.02352
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
best_oa_location.pdf_url	https://arxiv.org/pdf/2402.02352
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id	https://openalex.org/licenses/cc-by
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/2402.02352
primary_location.id	pmh:oai:arXiv.org:2402.02352
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
primary_location.pdf_url	https://arxiv.org/pdf/2402.02352
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2402.02352
publication_date	2024-02-04
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	12, 48
abstract_inverted_index.We	0, 27
abstract_inverted_index.be	36
abstract_inverted_index.in	14
abstract_inverted_index.it	95
abstract_inverted_index.of	51, 90
abstract_inverted_index.to	82, 97
abstract_inverted_index.SAM	34
abstract_inverted_index.The	88
abstract_inverted_index.and	19, 45, 59, 65, 100
abstract_inverted_index.are	5, 22, 67
abstract_inverted_index.but	17
abstract_inverted_index.can	35
abstract_inverted_index.for	7, 47
abstract_inverted_index.now	23
abstract_inverted_index.the	63, 91
abstract_inverted_index.Once	62
abstract_inverted_index.also	93
abstract_inverted_index.even	71
abstract_inverted_index.like	33, 43
abstract_inverted_index.many	106
abstract_inverted_index.once	11
abstract_inverted_index.show	28
abstract_inverted_index.that	29, 84
abstract_inverted_index.them	79
abstract_inverted_index.used	24, 46
abstract_inverted_index.well	80
abstract_inverted_index.were	10
abstract_inverted_index.wide	49
abstract_inverted_index.with	39, 72
abstract_inverted_index.image	57
abstract_inverted_index.makes	94
abstract_inverted_index.masks	64
abstract_inverted_index.other	101
abstract_inverted_index.pixel	18
abstract_inverted_index.these	69
abstract_inverted_index.video	98
abstract_inverted_index.DINOv2	44
abstract_inverted_index.across	105
abstract_inverted_index.almost	25
abstract_inverted_index.custom	86
abstract_inverted_index.enable	75
abstract_inverted_index.linear	73
abstract_inverted_index.making	78
abstract_inverted_index.recent	30
abstract_inverted_index.strong	40
abstract_inverted_index.suited	81
abstract_inverted_index.tasks,	52
abstract_inverted_index.Regions	9
abstract_inverted_index.images.	107
abstract_inverted_index.require	85
abstract_inverted_index.variety	50
abstract_inverted_index.whether	2
abstract_inverted_index.analysis	99
abstract_inverted_index.combined	38
abstract_inverted_index.features	21, 66
abstract_inverted_index.mainstay	13
abstract_inverted_index.problems	102
abstract_inverted_index.queries.	87
abstract_inverted_index.semantic	54
abstract_inverted_index.analysis.	61
abstract_inverted_index.decoders,	74
abstract_inverted_index.effective	6
abstract_inverted_index.including	53
abstract_inverted_index.inference	104
abstract_inverted_index.requiring	103
abstract_inverted_index.extracted,	68
abstract_inverted_index.retrieval,	58
abstract_inverted_index.segmenters	32
abstract_inverted_index.approaches,	16
abstract_inverted_index.compactness	89
abstract_inverted_index.competitive	76
abstract_inverted_index.effectively	37
abstract_inverted_index.investigate	1
abstract_inverted_index.multi-image	60
abstract_inverted_index.patch-based	20
abstract_inverted_index.recognition	15
abstract_inverted_index.well-suited	96
abstract_inverted_index.applications	83
abstract_inverted_index.exclusively.	26
abstract_inverted_index.object-based	56
abstract_inverted_index.performance,	77
abstract_inverted_index.recognition.	8
abstract_inverted_index.region-based	3
abstract_inverted_index.unsupervised	41
abstract_inverted_index.segmentation,	55
abstract_inverted_index.class-agnostic	31
abstract_inverted_index.representation	92
abstract_inverted_index.representations	4, 42
abstract_inverted_index.representations,	70
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	10
citation_normalized_percentile