The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing Article Swipe

PDF

Zheng Xu , Xitong Yang , Xue Li , Xiaoshuai Sun ·

YOU? · · 2018 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1805.03305

We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image. Instead of relying on hand-crafted image priors or explicitly estimating the components of the widely used atmospheric scattering model, our end-to-end system directly generates the clear image from an input hazy image. The proposed network has an encoder-decoder architecture with skip connections and instance normalization. We adopt the convolutional layers of the pre-trained VGG network as encoder to exploit the representation power of deep features, and demonstrate the effectiveness of instance normalization for image dehazing. Our simple yet effective network outperforms the state-of-the-art methods by a large margin on the benchmark datasets.

Related Topics

Computer Science

Artificial Intelligence

Benchmark (Surveying)

Convolutional Neural Network

Concepts

Normalization (sociology) Computer science Artificial intelligence Benchmark (surveying) Margin (machine learning) Convolutional neural network Encoder Network architecture Image (mathematics) Exploit Deep learning Pattern recognition (psychology) Prior probability Computer vision Machine learning Bayesian probability Computer security Sociology Geodesy Geography Anthropology Operating system

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/1805.03305
PDF: https://arxiv.org/pdf/1805.03305
OA Status: green
Cited By: 17
References: 35
Related Works: 10
OpenAlex ID: https://openalex.org/W2799814362

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W2799814362

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.1805.03305

Digital Object Identifier
Title: The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2018

Year of publication
Publication date: 2018-05-08

Full publication date if available
Authors: Zheng Xu, Xitong Yang, Xue Li, Xiaoshuai Sun

List of authors in order
Landing page: https://arxiv.org/abs/1805.03305

Publisher landing page
PDF URL: https://arxiv.org/pdf/1805.03305

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/1805.03305

Direct OA link when available
Concepts: Normalization (sociology), Computer science, Artificial intelligence, Benchmark (surveying), Margin (machine learning), Convolutional neural network, Encoder, Network architecture, Image (mathematics), Exploit, Deep learning, Pattern recognition (psychology), Prior probability, Computer vision, Machine learning, Bayesian probability, Computer security, Sociology, Geodesy, Geography, Anthropology, Operating system

Top concepts (fields/topics) attached by OpenAlex
Cited by: 17

Total citation count in OpenAlex
Citations by year (recent): 2025: 1, 2023: 1, 2022: 1, 2021: 5, 2020: 4

Per-year citation counts (last 5 years)
References (count): 35

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W2799814362
doi	https://doi.org/10.48550/arxiv.1805.03305
ids.doi	https://doi.org/10.48550/arxiv.1805.03305
ids.mag	2799814362
ids.openalex	https://openalex.org/W2799814362
fwci
type	preprint
title	The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11019
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	1.0
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	Image Enhancement Techniques
topics[1].id	https://openalex.org/T11105
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9969000220298767
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Advanced Image Processing Techniques
topics[2].id	https://openalex.org/T11659
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.9965000152587891
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2214
topics[2].subfield.display_name	Media Technology
topics[2].display_name	Advanced Image Fusion Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C136886441
concepts[0].level	2
concepts[0].score	0.8472923040390015
concepts[0].wikidata	https://www.wikidata.org/wiki/Q926129
concepts[0].display_name	Normalization (sociology)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.7842040061950684
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.7174984812736511
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C185798385
concepts[3].level	2
concepts[3].score	0.6434130668640137
concepts[3].wikidata	https://www.wikidata.org/wiki/Q1161707
concepts[3].display_name	Benchmark (surveying)
concepts[4].id	https://openalex.org/C774472
concepts[4].level	2
concepts[4].score	0.5985094904899597
concepts[4].wikidata	https://www.wikidata.org/wiki/Q6760393
concepts[4].display_name	Margin (machine learning)
concepts[5].id	https://openalex.org/C81363708
concepts[5].level	2
concepts[5].score	0.5908758044242859
concepts[5].wikidata	https://www.wikidata.org/wiki/Q17084460
concepts[5].display_name	Convolutional neural network
concepts[6].id	https://openalex.org/C118505674
concepts[6].level	2
concepts[6].score	0.54443359375
concepts[6].wikidata	https://www.wikidata.org/wiki/Q42586063
concepts[6].display_name	Encoder
concepts[7].id	https://openalex.org/C193415008
concepts[7].level	2
concepts[7].score	0.5265489220619202
concepts[7].wikidata	https://www.wikidata.org/wiki/Q639681
concepts[7].display_name	Network architecture
concepts[8].id	https://openalex.org/C115961682
concepts[8].level	2
concepts[8].score	0.5105763673782349
concepts[8].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[8].display_name	Image (mathematics)
concepts[9].id	https://openalex.org/C165696696
concepts[9].level	2
concepts[9].score	0.5046128034591675
concepts[9].wikidata	https://www.wikidata.org/wiki/Q11287
concepts[9].display_name	Exploit
concepts[10].id	https://openalex.org/C108583219
concepts[10].level	2
concepts[10].score	0.464733362197876
concepts[10].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[10].display_name	Deep learning
concepts[11].id	https://openalex.org/C153180895
concepts[11].level	2
concepts[11].score	0.46317464113235474
concepts[11].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[11].display_name	Pattern recognition (psychology)
concepts[12].id	https://openalex.org/C177769412
concepts[12].level	3
concepts[12].score	0.4485885500907898
concepts[12].wikidata	https://www.wikidata.org/wiki/Q278090
concepts[12].display_name	Prior probability
concepts[13].id	https://openalex.org/C31972630
concepts[13].level	1
concepts[13].score	0.4009994864463806
concepts[13].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[13].display_name	Computer vision
concepts[14].id	https://openalex.org/C119857082
concepts[14].level	1
concepts[14].score	0.20593580603599548
concepts[14].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[14].display_name	Machine learning
concepts[15].id	https://openalex.org/C107673813
concepts[15].level	2
concepts[15].score	0.058459341526031494
concepts[15].wikidata	https://www.wikidata.org/wiki/Q812534
concepts[15].display_name	Bayesian probability
concepts[16].id	https://openalex.org/C38652104
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q3510521
concepts[16].display_name	Computer security
concepts[17].id	https://openalex.org/C144024400
concepts[17].level	0
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q21201
concepts[17].display_name	Sociology
concepts[18].id	https://openalex.org/C13280743
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q131089
concepts[18].display_name	Geodesy
concepts[19].id	https://openalex.org/C205649164
concepts[19].level	0
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q1071
concepts[19].display_name	Geography
concepts[20].id	https://openalex.org/C19165224
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q23404
concepts[20].display_name	Anthropology
concepts[21].id	https://openalex.org/C111919701
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q9135
concepts[21].display_name	Operating system
keywords[0].id	https://openalex.org/keywords/normalization
keywords[0].score	0.8472923040390015
keywords[0].display_name	Normalization (sociology)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.7842040061950684
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.7174984812736511
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/benchmark
keywords[3].score	0.6434130668640137
keywords[3].display_name	Benchmark (surveying)
keywords[4].id	https://openalex.org/keywords/margin
keywords[4].score	0.5985094904899597
keywords[4].display_name	Margin (machine learning)
keywords[5].id	https://openalex.org/keywords/convolutional-neural-network
keywords[5].score	0.5908758044242859
keywords[5].display_name	Convolutional neural network
keywords[6].id	https://openalex.org/keywords/encoder
keywords[6].score	0.54443359375
keywords[6].display_name	Encoder
keywords[7].id	https://openalex.org/keywords/network-architecture
keywords[7].score	0.5265489220619202
keywords[7].display_name	Network architecture
keywords[8].id	https://openalex.org/keywords/image
keywords[8].score	0.5105763673782349
keywords[8].display_name	Image (mathematics)
keywords[9].id	https://openalex.org/keywords/exploit
keywords[9].score	0.5046128034591675
keywords[9].display_name	Exploit
keywords[10].id	https://openalex.org/keywords/deep-learning
keywords[10].score	0.464733362197876
keywords[10].display_name	Deep learning
keywords[11].id	https://openalex.org/keywords/pattern-recognition
keywords[11].score	0.46317464113235474
keywords[11].display_name	Pattern recognition (psychology)
keywords[12].id	https://openalex.org/keywords/prior-probability
keywords[12].score	0.4485885500907898
keywords[12].display_name	Prior probability
keywords[13].id	https://openalex.org/keywords/computer-vision
keywords[13].score	0.4009994864463806
keywords[13].display_name	Computer vision
keywords[14].id	https://openalex.org/keywords/machine-learning
keywords[14].score	0.20593580603599548
keywords[14].display_name	Machine learning
keywords[15].id	https://openalex.org/keywords/bayesian-probability
keywords[15].score	0.058459341526031494
keywords[15].display_name	Bayesian probability
language	en
locations[0].id	pmh:oai:arXiv.org:1805.03305
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/1805.03305
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/1805.03305
locations[1].id	doi:10.48550/arxiv.1805.03305
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.1805.03305
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101651955
authorships[0].author.orcid	https://orcid.org/0009-0003-6747-3953
authorships[0].author.display_name	Zheng Xu
authorships[0].author_position	first
authorships[0].raw_author_name	Zheng Xu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5091064356
authorships[1].author.orcid	https://orcid.org/0000-0003-4372-241X
authorships[1].author.display_name	Xitong Yang
authorships[1].author_position	middle
authorships[1].raw_author_name	Xitong Yang
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100372201
authorships[2].author.orcid	https://orcid.org/0000-0002-4515-6792
authorships[2].author.display_name	Xue Li
authorships[2].author_position	middle
authorships[2].raw_author_name	Xue Li
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5059926864
authorships[3].author.orcid	https://orcid.org/0000-0003-3912-9306
authorships[3].author.display_name	Xiaoshuai Sun
authorships[3].author_position	last
authorships[3].raw_author_name	Xiaoshuai Sun
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/1805.03305
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2018-05-17T00:00:00
display_name	The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11019
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	1.0
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	Image Enhancement Techniques
related_works	https://openalex.org/W2580650124, https://openalex.org/W4386190339, https://openalex.org/W2968424575, https://openalex.org/W3142333283, https://openalex.org/W3122088529, https://openalex.org/W3041320102, https://openalex.org/W2111669074, https://openalex.org/W2085259108, https://openalex.org/W3123087812, https://openalex.org/W2063076820
cited_by_count	17
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2023
counts_by_year[1].cited_by_count	1
counts_by_year[2].year	2022
counts_by_year[2].cited_by_count	1
counts_by_year[3].year	2021
counts_by_year[3].cited_by_count	5
counts_by_year[4].year	2020
counts_by_year[4].cited_by_count	4
counts_by_year[5].year	2019
counts_by_year[5].cited_by_count	3
counts_by_year[6].year	2018
counts_by_year[6].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:1805.03305
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/1805.03305
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/1805.03305
primary_location.id	pmh:oai:arXiv.org:1805.03305
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/1805.03305
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/1805.03305
publication_date	2018-05-08
publication_year	2018
referenced_works	https://openalex.org/W2065002911, https://openalex.org/W2793308355, https://openalex.org/W2963525668, https://openalex.org/W2991006905, https://openalex.org/W2028990532, https://openalex.org/W2962782447, https://openalex.org/W2114867966, https://openalex.org/W63091017, https://openalex.org/W2117539524, https://openalex.org/W2475287302, https://openalex.org/W2748021867, https://openalex.org/W2156936307, https://openalex.org/W2121880036, https://openalex.org/W2536722097, https://openalex.org/W2779176852, https://openalex.org/W2951004968, https://openalex.org/W2788682721, https://openalex.org/W2798031977, https://openalex.org/W1901129140, https://openalex.org/W2155541015, https://openalex.org/W2771305881, https://openalex.org/W2518979500, https://openalex.org/W2949117887, https://openalex.org/W2791550762, https://openalex.org/W125693051, https://openalex.org/W2502312327, https://openalex.org/W2796555273, https://openalex.org/W2128254161, https://openalex.org/W2783879794, https://openalex.org/W2028763589, https://openalex.org/W2467473805, https://openalex.org/W1686810756, https://openalex.org/W2951697117, https://openalex.org/W2797809360, https://openalex.org/W2194775991
referenced_works_count	35
abstract_inverted_index.a	2, 24, 113
abstract_inverted_index.We	0, 73
abstract_inverted_index.an	56, 64
abstract_inverted_index.as	83
abstract_inverted_index.by	112
abstract_inverted_index.of	12, 29, 40, 78, 90, 97
abstract_inverted_index.on	31, 116
abstract_inverted_index.or	35
abstract_inverted_index.to	18, 85
abstract_inverted_index.Our	103
abstract_inverted_index.The	60
abstract_inverted_index.VGG	81
abstract_inverted_index.and	70, 93
abstract_inverted_index.for	8, 100
abstract_inverted_index.has	63
abstract_inverted_index.our	47
abstract_inverted_index.the	9, 20, 38, 41, 52, 75, 79, 87, 95, 109, 117
abstract_inverted_index.yet	105
abstract_inverted_index.aims	17
abstract_inverted_index.deep	4, 91
abstract_inverted_index.from	23, 55
abstract_inverted_index.hazy	26, 58
abstract_inverted_index.skip	68
abstract_inverted_index.used	43
abstract_inverted_index.with	67
abstract_inverted_index.adopt	74
abstract_inverted_index.clear	21, 53
abstract_inverted_index.image	14, 22, 33, 54, 101
abstract_inverted_index.input	57
abstract_inverted_index.large	114
abstract_inverted_index.novel	3
abstract_inverted_index.power	89
abstract_inverted_index.which	16
abstract_inverted_index.image.	27, 59
abstract_inverted_index.layers	77
abstract_inverted_index.margin	115
abstract_inverted_index.model,	46
abstract_inverted_index.neural	5
abstract_inverted_index.priors	34
abstract_inverted_index.simple	104
abstract_inverted_index.single	13
abstract_inverted_index.system	49
abstract_inverted_index.widely	42
abstract_inverted_index.Instead	28
abstract_inverted_index.encoder	84
abstract_inverted_index.exploit	86
abstract_inverted_index.methods	111
abstract_inverted_index.network	6, 62, 82, 107
abstract_inverted_index.problem	11
abstract_inverted_index.propose	1
abstract_inverted_index.recover	19
abstract_inverted_index.relying	30
abstract_inverted_index.degraded	25
abstract_inverted_index.directly	50
abstract_inverted_index.instance	71, 98
abstract_inverted_index.proposed	61
abstract_inverted_index.benchmark	118
abstract_inverted_index.datasets.	119
abstract_inverted_index.dehazing,	15
abstract_inverted_index.dehazing.	102
abstract_inverted_index.effective	106
abstract_inverted_index.features,	92
abstract_inverted_index.generates	51
abstract_inverted_index.components	39
abstract_inverted_index.end-to-end	48
abstract_inverted_index.estimating	37
abstract_inverted_index.explicitly	36
abstract_inverted_index.scattering	45
abstract_inverted_index.atmospheric	44
abstract_inverted_index.challenging	10
abstract_inverted_index.connections	69
abstract_inverted_index.demonstrate	94
abstract_inverted_index.outperforms	108
abstract_inverted_index.pre-trained	80
abstract_inverted_index.architecture	7, 66
abstract_inverted_index.hand-crafted	32
abstract_inverted_index.convolutional	76
abstract_inverted_index.effectiveness	96
abstract_inverted_index.normalization	99
abstract_inverted_index.normalization.	72
abstract_inverted_index.representation	88
abstract_inverted_index.encoder-decoder	65
abstract_inverted_index.state-of-the-art	110
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile