Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach Article Swipe

PDF

Qi Zhang , Shanshe Wang , Xinfeng Zhang , Siwei Ma , Jingshan Pan , Wen Gao ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.17477

Nowadays, high-quality images are pursued by both humans for better viewing experience and by machines for more accurate visual analysis. However, images are usually compressed before being consumed, decreasing their quality. It is meaningful to predict the perceptual quality of compressed images for both humans and machines, which guides the optimization for compression. In this paper, we propose a unified approach to address this. Specifically, we create a deep learning-based model to predict Satisfied User Ratio (SUR) and Satisfied Machine Ratio (SMR) of compressed images simultaneously. We first pre-train a feature extractor network on a large-scale SMR-annotated dataset with human perception-related quality labels generated by diverse image quality models, which simulates the acquisition of SUR labels. Then, we propose an MLP-Mixer-based network to predict SUR and SMR by leveraging and fusing the extracted multi-layer features. We introduce a Difference Feature Residual Learning (DFRL) module to learn more discriminative difference features. We further use a Multi-Head Attention Aggregation and Pooling (MHAAP) layer to aggregate difference features and reduce their redundancy. Experimental results indicate that the proposed model significantly outperforms state-of-the-art SUR and SMR prediction methods. Moreover, our joint learning scheme of human and machine perceptual quality prediction tasks is effective at improving the performance of both.

Related Topics

Computer Science

Artificial Intelligence

Machine Learning

Computer Vision

Concepts

Computer science Compressed sensing Artificial intelligence Machine learning Computer vision

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2412.17477
PDF: https://arxiv.org/pdf/2412.17477
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4405767904

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405767904

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2412.17477

Digital Object Identifier
Title: Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-12-23

Full publication date if available
Authors: Qi Zhang, Shanshe Wang, Xinfeng Zhang, Siwei Ma, Jingshan Pan, Wen Gao

List of authors in order
Landing page: https://arxiv.org/abs/2412.17477

Publisher landing page
PDF URL: https://arxiv.org/pdf/2412.17477

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/2412.17477

Direct OA link when available
Concepts: Computer science, Compressed sensing, Artificial intelligence, Machine learning, Computer vision

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/W4405767904
doi	https://doi.org/10.48550/arxiv.2412.17477
ids.doi	https://doi.org/10.48550/arxiv.2412.17477
ids.openalex	https://openalex.org/W4405767904
fwci
type	preprint
title	Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11165
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9894999861717224
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 and Video Quality Assessment
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.6082046031951904
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C124851039
concepts[1].level	2
concepts[1].score	0.4942190945148468
concepts[1].wikidata	https://www.wikidata.org/wiki/Q2665459
concepts[1].display_name	Compressed sensing
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.45362889766693115
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C119857082
concepts[3].level	1
concepts[3].score	0.3622059226036072
concepts[3].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[3].display_name	Machine learning
concepts[4].id	https://openalex.org/C31972630
concepts[4].level	1
concepts[4].score	0.34044450521469116
concepts[4].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[4].display_name	Computer vision
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.6082046031951904
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/compressed-sensing
keywords[1].score	0.4942190945148468
keywords[1].display_name	Compressed sensing
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.45362889766693115
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/machine-learning
keywords[3].score	0.3622059226036072
keywords[3].display_name	Machine learning
keywords[4].id	https://openalex.org/keywords/computer-vision
keywords[4].score	0.34044450521469116
keywords[4].display_name	Computer vision
language	en
locations[0].id	pmh:oai:arXiv.org:2412.17477
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/2412.17477
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/2412.17477
locations[1].id	doi:10.48550/arxiv.2412.17477
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.2412.17477
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5100348829
authorships[0].author.orcid	https://orcid.org/0000-0001-7041-643X
authorships[0].author.display_name	Qi Zhang
authorships[0].author_position	first
authorships[0].raw_author_name	Zhang, Qi
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100385183
authorships[1].author.orcid
authorships[1].author.display_name	Shanshe Wang
authorships[1].author_position	middle
authorships[1].raw_author_name	Wang, Shanshe
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5055937409
authorships[2].author.orcid	https://orcid.org/0000-0002-7517-3868
authorships[2].author.display_name	Xinfeng Zhang
authorships[2].author_position	middle
authorships[2].raw_author_name	Zhang, Xinfeng
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5039832462
authorships[3].author.orcid	https://orcid.org/0000-0002-2731-5403
authorships[3].author.display_name	Siwei Ma
authorships[3].author_position	middle
authorships[3].raw_author_name	Ma, Siwei
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5026533187
authorships[4].author.orcid	https://orcid.org/0009-0002-0968-0658
authorships[4].author.display_name	Jingshan Pan
authorships[4].author_position	middle
authorships[4].raw_author_name	Pan, Jingshan
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5018478553
authorships[5].author.orcid	https://orcid.org/0000-0002-8070-802X
authorships[5].author.display_name	Wen Gao
authorships[5].author_position	last
authorships[5].raw_author_name	Gao, Wen
authorships[5].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/2412.17477
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-12-25T00:00:00
display_name	Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11165
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9894999861717224
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 and Video Quality Assessment
related_works	https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W2772917594, https://openalex.org/W2036807459, https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2412.17477
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/2412.17477
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/2412.17477
primary_location.id	pmh:oai:arXiv.org:2412.17477
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/2412.17477
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/2412.17477
publication_date	2024-12-23
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	58, 67, 89, 94, 137, 153
abstract_inverted_index.In	53
abstract_inverted_index.It	31
abstract_inverted_index.We	86, 135, 150
abstract_inverted_index.an	119
abstract_inverted_index.at	199
abstract_inverted_index.by	5, 13, 104, 127
abstract_inverted_index.is	32, 197
abstract_inverted_index.of	39, 82, 113, 189, 203
abstract_inverted_index.on	93
abstract_inverted_index.to	34, 61, 71, 122, 144, 161
abstract_inverted_index.we	56, 65, 117
abstract_inverted_index.SMR	126, 181
abstract_inverted_index.SUR	114, 124, 179
abstract_inverted_index.and	12, 45, 77, 125, 129, 157, 165, 180, 191
abstract_inverted_index.are	3, 22
abstract_inverted_index.for	8, 15, 42, 51
abstract_inverted_index.our	185
abstract_inverted_index.the	36, 49, 111, 131, 173, 201
abstract_inverted_index.use	152
abstract_inverted_index.User	74
abstract_inverted_index.both	6, 43
abstract_inverted_index.deep	68
abstract_inverted_index.more	16, 146
abstract_inverted_index.that	172
abstract_inverted_index.this	54
abstract_inverted_index.with	98
abstract_inverted_index.(SMR)	81
abstract_inverted_index.(SUR)	76
abstract_inverted_index.Ratio	75, 80
abstract_inverted_index.Then,	116
abstract_inverted_index.being	26
abstract_inverted_index.both.	204
abstract_inverted_index.first	87
abstract_inverted_index.human	99, 190
abstract_inverted_index.image	106
abstract_inverted_index.joint	186
abstract_inverted_index.layer	160
abstract_inverted_index.learn	145
abstract_inverted_index.model	70, 175
abstract_inverted_index.tasks	196
abstract_inverted_index.their	29, 167
abstract_inverted_index.this.	63
abstract_inverted_index.which	47, 109
abstract_inverted_index.(DFRL)	142
abstract_inverted_index.before	25
abstract_inverted_index.better	9
abstract_inverted_index.create	66
abstract_inverted_index.fusing	130
abstract_inverted_index.guides	48
abstract_inverted_index.humans	7, 44
abstract_inverted_index.images	2, 21, 41, 84
abstract_inverted_index.labels	102
abstract_inverted_index.module	143
abstract_inverted_index.paper,	55
abstract_inverted_index.reduce	166
abstract_inverted_index.scheme	188
abstract_inverted_index.visual	18
abstract_inverted_index.(MHAAP)	159
abstract_inverted_index.Feature	139
abstract_inverted_index.Machine	79
abstract_inverted_index.Pooling	158
abstract_inverted_index.address	62
abstract_inverted_index.dataset	97
abstract_inverted_index.diverse	105
abstract_inverted_index.feature	90
abstract_inverted_index.further	151
abstract_inverted_index.labels.	115
abstract_inverted_index.machine	192
abstract_inverted_index.models,	108
abstract_inverted_index.network	92, 121
abstract_inverted_index.predict	35, 72, 123
abstract_inverted_index.propose	57, 118
abstract_inverted_index.pursued	4
abstract_inverted_index.quality	38, 101, 107, 194
abstract_inverted_index.results	170
abstract_inverted_index.unified	59
abstract_inverted_index.usually	23
abstract_inverted_index.viewing	10
abstract_inverted_index.However,	20
abstract_inverted_index.Learning	141
abstract_inverted_index.Residual	140
abstract_inverted_index.accurate	17
abstract_inverted_index.approach	60
abstract_inverted_index.features	164
abstract_inverted_index.indicate	171
abstract_inverted_index.learning	187
abstract_inverted_index.machines	14
abstract_inverted_index.methods.	183
abstract_inverted_index.proposed	174
abstract_inverted_index.quality.	30
abstract_inverted_index.Attention	155
abstract_inverted_index.Moreover,	184
abstract_inverted_index.Nowadays,	0
abstract_inverted_index.Satisfied	73, 78
abstract_inverted_index.aggregate	162
abstract_inverted_index.analysis.	19
abstract_inverted_index.consumed,	27
abstract_inverted_index.effective	198
abstract_inverted_index.extracted	132
abstract_inverted_index.extractor	91
abstract_inverted_index.features.	134, 149
abstract_inverted_index.generated	103
abstract_inverted_index.improving	200
abstract_inverted_index.introduce	136
abstract_inverted_index.machines,	46
abstract_inverted_index.pre-train	88
abstract_inverted_index.simulates	110
abstract_inverted_index.Difference	138
abstract_inverted_index.Multi-Head	154
abstract_inverted_index.compressed	24, 40, 83
abstract_inverted_index.decreasing	28
abstract_inverted_index.difference	148, 163
abstract_inverted_index.experience	11
abstract_inverted_index.leveraging	128
abstract_inverted_index.meaningful	33
abstract_inverted_index.perceptual	37, 193
abstract_inverted_index.prediction	182, 195
abstract_inverted_index.Aggregation	156
abstract_inverted_index.acquisition	112
abstract_inverted_index.large-scale	95
abstract_inverted_index.multi-layer	133
abstract_inverted_index.outperforms	177
abstract_inverted_index.performance	202
abstract_inverted_index.redundancy.	168
abstract_inverted_index.Experimental	169
abstract_inverted_index.compression.	52
abstract_inverted_index.high-quality	1
abstract_inverted_index.optimization	50
abstract_inverted_index.SMR-annotated	96
abstract_inverted_index.Specifically,	64
abstract_inverted_index.significantly	176
abstract_inverted_index.discriminative	147
abstract_inverted_index.learning-based	69
abstract_inverted_index.MLP-Mixer-based	120
abstract_inverted_index.simultaneously.	85
abstract_inverted_index.state-of-the-art	178
abstract_inverted_index.perception-related	100
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile