CALLIC: Content Adaptive Learning for Lossless Image Compression Article Swipe

PDF

Daxin Li , Yuanchao Bai , Kai Wang , Junjun Jiang , Xianming Liu , Wen Gao ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.1609/aaai.v39i5.32494

Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution estimation for specific testing images during encoding process. To address this challenge, we explore the connection between the Minimum Description Length (MDL) principle and Parameter-Efficient Transfer Learning (PETL), leading to the development of a novel content-adaptive approach for learned lossless image compression, dubbed CALLIC. Specifically, we first propose a content-aware autoregressive self-attention mechanism by leveraging convolutional gating operations, termed Masked Gated ConvFormer (MGCF), and pretrain MGCF on training dataset. Cache then Crop Inference (CCI) is proposed to accelerate the coding process. During encoding, we decompose pretrained layers, including depth-wise convolutions, using low-rank matrices and then adapt the incremental weights on testing image by Rate-guided Progressive Fine-Tuning (RPFT). RPFT fine-tunes with gradually increasing patches that are sorted in descending order by estimated entropy, optimizing learning process and reducing adaptation time. Extensive experiments across diverse datasets demonstrate that CALLIC sets a new state-of-the-art (SOTA) for learned lossless image compression.

Related Topics

Computer Science

Image Compression

Artificial Intelligence

Computer Vision

Mathematics

Mathematical Analysis

Concepts

Lossless compression Computer science Image compression Content (measure theory) Artificial intelligence Data compression Computer vision Image (mathematics) Image processing Mathematics Mathematical analysis

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.1609/aaai.v39i5.32494
PDF: https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649
OA Status: diamond
Cited By: 3
Related Works: 10
OpenAlex ID: https://openalex.org/W4409367330

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4409367330

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1609/aaai.v39i5.32494

Digital Object Identifier
Title: CALLIC: Content Adaptive Learning for Lossless Image Compression

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-04-11

Full publication date if available
Authors: Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu, Wen Gao

List of authors in order
Landing page: https://doi.org/10.1609/aaai.v39i5.32494

Publisher landing page
PDF URL: https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649

Direct OA link when available
Concepts: Lossless compression, Computer science, Image compression, Content (measure theory), Artificial intelligence, Data compression, Computer vision, Image (mathematics), Image processing, Mathematics, Mathematical analysis

Top concepts (fields/topics) attached by OpenAlex
Cited by: 3

Total citation count in OpenAlex
Citations by year (recent): 2025: 3

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

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4409367330
doi	https://doi.org/10.1609/aaai.v39i5.32494
ids.doi	https://doi.org/10.1609/aaai.v39i5.32494
ids.openalex	https://openalex.org/W4409367330
fwci	5.50240386
type	article
title	CALLIC: Content Adaptive Learning for Lossless Image Compression
biblio.issue	5
biblio.volume	39
biblio.last_page	4688
biblio.first_page	4679
topics[0].id	https://openalex.org/T10901
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9983000159263611
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	Advanced Data Compression Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C81081738
concepts[0].level	3
concepts[0].score	0.8310348987579346
concepts[0].wikidata	https://www.wikidata.org/wiki/Q55542
concepts[0].display_name	Lossless compression
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.604856014251709
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C13481523
concepts[2].level	4
concepts[2].score	0.597467303276062
concepts[2].wikidata	https://www.wikidata.org/wiki/Q412438
concepts[2].display_name	Image compression
concepts[3].id	https://openalex.org/C2778152352
concepts[3].level	2
concepts[3].score	0.5214293003082275
concepts[3].wikidata	https://www.wikidata.org/wiki/Q5165061
concepts[3].display_name	Content (measure theory)
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.4105762541294098
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C78548338
concepts[5].level	2
concepts[5].score	0.38919779658317566
concepts[5].wikidata	https://www.wikidata.org/wiki/Q2493
concepts[5].display_name	Data compression
concepts[6].id	https://openalex.org/C31972630
concepts[6].level	1
concepts[6].score	0.38666030764579773
concepts[6].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[6].display_name	Computer vision
concepts[7].id	https://openalex.org/C115961682
concepts[7].level	2
concepts[7].score	0.3741183280944824
concepts[7].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[7].display_name	Image (mathematics)
concepts[8].id	https://openalex.org/C9417928
concepts[8].level	3
concepts[8].score	0.20602065324783325
concepts[8].wikidata	https://www.wikidata.org/wiki/Q1070689
concepts[8].display_name	Image processing
concepts[9].id	https://openalex.org/C33923547
concepts[9].level	0
concepts[9].score	0.17691227793693542
concepts[9].wikidata	https://www.wikidata.org/wiki/Q395
concepts[9].display_name	Mathematics
concepts[10].id	https://openalex.org/C134306372
concepts[10].level	1
concepts[10].score	0.0
concepts[10].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[10].display_name	Mathematical analysis
keywords[0].id	https://openalex.org/keywords/lossless-compression
keywords[0].score	0.8310348987579346
keywords[0].display_name	Lossless compression
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.604856014251709
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/image-compression
keywords[2].score	0.597467303276062
keywords[2].display_name	Image compression
keywords[3].id	https://openalex.org/keywords/content
keywords[3].score	0.5214293003082275
keywords[3].display_name	Content (measure theory)
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.4105762541294098
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/data-compression
keywords[5].score	0.38919779658317566
keywords[5].display_name	Data compression
keywords[6].id	https://openalex.org/keywords/computer-vision
keywords[6].score	0.38666030764579773
keywords[6].display_name	Computer vision
keywords[7].id	https://openalex.org/keywords/image
keywords[7].score	0.3741183280944824
keywords[7].display_name	Image (mathematics)
keywords[8].id	https://openalex.org/keywords/image-processing
keywords[8].score	0.20602065324783325
keywords[8].display_name	Image processing
keywords[9].id	https://openalex.org/keywords/mathematics
keywords[9].score	0.17691227793693542
keywords[9].display_name	Mathematics
language	en
locations[0].id	doi:10.1609/aaai.v39i5.32494
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210191458
locations[0].source.issn	2159-5399, 2374-3468
locations[0].source.type	conference
locations[0].source.is_oa	True
locations[0].source.issn_l	2159-5399
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	Proceedings of the AAAI Conference on Artificial Intelligence
locations[0].source.host_organization	https://openalex.org/P4310320058
locations[0].source.host_organization_name	Association for the Advancement of Artificial Intelligence
locations[0].source.host_organization_lineage	https://openalex.org/P4310320058
locations[0].source.host_organization_lineage_names	Association for the Advancement of Artificial Intelligence
locations[0].license
locations[0].pdf_url	https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the AAAI Conference on Artificial Intelligence
locations[0].landing_page_url	https://doi.org/10.1609/aaai.v39i5.32494
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5007227942
authorships[0].author.orcid	https://orcid.org/0009-0001-6886-3342
authorships[0].author.display_name	Daxin Li
authorships[0].author_position	first
authorships[0].raw_author_name	Daxin Li
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5024093994
authorships[1].author.orcid	https://orcid.org/0000-0003-3449-6537
authorships[1].author.display_name	Yuanchao Bai
authorships[1].author_position	middle
authorships[1].raw_author_name	Yuanchao Bai
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100766811
authorships[2].author.orcid	https://orcid.org/0009-0007-3132-0495
authorships[2].author.display_name	Kai Wang
authorships[2].author_position	middle
authorships[2].raw_author_name	Kai Wang
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5087165831
authorships[3].author.orcid	https://orcid.org/0000-0002-5694-505X
authorships[3].author.display_name	Junjun Jiang
authorships[3].author_position	middle
authorships[3].raw_author_name	Junjun Jiang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100654390
authorships[4].author.orcid	https://orcid.org/0000-0002-8857-1785
authorships[4].author.display_name	Xianming Liu
authorships[4].author_position	middle
authorships[4].raw_author_name	Xianming Liu
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	Wen Gao
authorships[5].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://ojs.aaai.org/index.php/AAAI/article/download/32494/34649
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	CALLIC: Content Adaptive Learning for Lossless Image Compression
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T10901
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9983000159263611
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	Advanced Data Compression Techniques
related_works	https://openalex.org/W2948148442, https://openalex.org/W3210332869, https://openalex.org/W2461250372, https://openalex.org/W2521595930, https://openalex.org/W4313046148, https://openalex.org/W2751842002, https://openalex.org/W2161981399, https://openalex.org/W3180760233, https://openalex.org/W2096442341, https://openalex.org/W4210455546
cited_by_count	3
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	3
locations_count	1
best_oa_location.id	doi:10.1609/aaai.v39i5.32494
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210191458
best_oa_location.source.issn	2159-5399, 2374-3468
best_oa_location.source.type	conference
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	2159-5399
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	Proceedings of the AAAI Conference on Artificial Intelligence
best_oa_location.source.host_organization	https://openalex.org/P4310320058
best_oa_location.source.host_organization_name	Association for the Advancement of Artificial Intelligence
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310320058
best_oa_location.source.host_organization_lineage_names	Association for the Advancement of Artificial Intelligence
best_oa_location.license
best_oa_location.pdf_url	https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the AAAI Conference on Artificial Intelligence
best_oa_location.landing_page_url	https://doi.org/10.1609/aaai.v39i5.32494
primary_location.id	doi:10.1609/aaai.v39i5.32494
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210191458
primary_location.source.issn	2159-5399, 2374-3468
primary_location.source.type	conference
primary_location.source.is_oa	True
primary_location.source.issn_l	2159-5399
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	Proceedings of the AAAI Conference on Artificial Intelligence
primary_location.source.host_organization	https://openalex.org/P4310320058
primary_location.source.host_organization_name	Association for the Advancement of Artificial Intelligence
primary_location.source.host_organization_lineage	https://openalex.org/P4310320058
primary_location.source.host_organization_lineage_names	Association for the Advancement of Artificial Intelligence
primary_location.license
primary_location.pdf_url	https://ojs.aaai.org/index.php/AAAI/article/download/32494/34649
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the AAAI Conference on Artificial Intelligence
primary_location.landing_page_url	https://doi.org/10.1609/aaai.v39i5.32494
publication_date	2025-04-11
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	62, 77, 167
abstract_inverted_index.To	37
abstract_inverted_index.by	82, 131, 148
abstract_inverted_index.in	8, 25, 145
abstract_inverted_index.is	103
abstract_inverted_index.of	61
abstract_inverted_index.on	16, 21, 95, 128
abstract_inverted_index.to	58, 105
abstract_inverted_index.we	41, 74, 112
abstract_inverted_index.and	52, 92, 122, 154
abstract_inverted_index.are	143
abstract_inverted_index.for	30, 66, 171
abstract_inverted_index.has	4
abstract_inverted_index.new	168
abstract_inverted_index.the	43, 46, 59, 107, 125
abstract_inverted_index.Crop	100
abstract_inverted_index.MGCF	94
abstract_inverted_index.RPFT	136
abstract_inverted_index.rely	15
abstract_inverted_index.sets	166
abstract_inverted_index.that	142, 164
abstract_inverted_index.then	99, 123
abstract_inverted_index.this	39
abstract_inverted_index.with	138
abstract_inverted_index.(CCI)	102
abstract_inverted_index.(MDL)	50
abstract_inverted_index.Cache	98
abstract_inverted_index.Gated	89
abstract_inverted_index.adapt	124
abstract_inverted_index.first	75
abstract_inverted_index.image	2, 69, 130, 174
abstract_inverted_index.novel	63
abstract_inverted_index.often	14
abstract_inverted_index.order	147
abstract_inverted_index.time.	157
abstract_inverted_index.using	119
abstract_inverted_index.(SOTA)	170
abstract_inverted_index.CALLIC	165
abstract_inverted_index.During	110
abstract_inverted_index.Length	49
abstract_inverted_index.Masked	88
abstract_inverted_index.across	160
abstract_inverted_index.coding	108
abstract_inverted_index.dubbed	71
abstract_inverted_index.during	34
abstract_inverted_index.gating	85
abstract_inverted_index.images	33
abstract_inverted_index.models	20
abstract_inverted_index.recent	9
abstract_inverted_index.sorted	144
abstract_inverted_index.termed	87
abstract_inverted_index.years.	10
abstract_inverted_index.(MGCF),	91
abstract_inverted_index.(PETL),	56
abstract_inverted_index.(RPFT).	135
abstract_inverted_index.CALLIC.	72
abstract_inverted_index.Learned	0
abstract_inverted_index.Minimum	47
abstract_inverted_index.address	38
abstract_inverted_index.between	45
abstract_inverted_index.diverse	161
abstract_inverted_index.explore	42
abstract_inverted_index.layers,	115
abstract_inverted_index.leading	57
abstract_inverted_index.learned	67, 172
abstract_inverted_index.massive	22
abstract_inverted_index.methods	13
abstract_inverted_index.patches	141
abstract_inverted_index.process	153
abstract_inverted_index.propose	76
abstract_inverted_index.testing	32, 129
abstract_inverted_index.weights	127
abstract_inverted_index.However,	11
abstract_inverted_index.Learning	55
abstract_inverted_index.Transfer	54
abstract_inverted_index.achieved	5
abstract_inverted_index.approach	65
abstract_inverted_index.dataset.	97
abstract_inverted_index.datasets	162
abstract_inverted_index.encoding	35
abstract_inverted_index.entropy,	150
abstract_inverted_index.existing	12
abstract_inverted_index.learning	152
abstract_inverted_index.lossless	1, 68, 173
abstract_inverted_index.low-rank	120
abstract_inverted_index.matrices	121
abstract_inverted_index.pretrain	93
abstract_inverted_index.process.	36, 109
abstract_inverted_index.proposed	104
abstract_inverted_index.reducing	155
abstract_inverted_index.specific	31
abstract_inverted_index.training	17, 96
abstract_inverted_index.Extensive	158
abstract_inverted_index.Inference	101
abstract_inverted_index.amortized	18
abstract_inverted_index.datasets,	23
abstract_inverted_index.decompose	113
abstract_inverted_index.encoding,	111
abstract_inverted_index.estimated	149
abstract_inverted_index.gradually	139
abstract_inverted_index.including	116
abstract_inverted_index.mechanism	81
abstract_inverted_index.principle	51
abstract_inverted_index.resulting	24
abstract_inverted_index.ConvFormer	90
abstract_inverted_index.accelerate	106
abstract_inverted_index.adaptation	156
abstract_inverted_index.challenge,	40
abstract_inverted_index.connection	44
abstract_inverted_index.depth-wise	117
abstract_inverted_index.descending	146
abstract_inverted_index.estimation	29
abstract_inverted_index.fine-tunes	137
abstract_inverted_index.generative	19
abstract_inverted_index.increasing	140
abstract_inverted_index.leveraging	83
abstract_inverted_index.optimizing	151
abstract_inverted_index.pretrained	114
abstract_inverted_index.Description	48
abstract_inverted_index.Fine-Tuning	134
abstract_inverted_index.Progressive	133
abstract_inverted_index.Rate-guided	132
abstract_inverted_index.compression	3
abstract_inverted_index.demonstrate	163
abstract_inverted_index.development	60
abstract_inverted_index.experiments	159
abstract_inverted_index.incremental	126
abstract_inverted_index.operations,	86
abstract_inverted_index.probability	27
abstract_inverted_index.significant	6
abstract_inverted_index.sub-optimal	26
abstract_inverted_index.advancements	7
abstract_inverted_index.compression,	70
abstract_inverted_index.compression.	175
abstract_inverted_index.distribution	28
abstract_inverted_index.Specifically,	73
abstract_inverted_index.content-aware	78
abstract_inverted_index.convolutional	84
abstract_inverted_index.convolutions,	118
abstract_inverted_index.autoregressive	79
abstract_inverted_index.self-attention	80
abstract_inverted_index.content-adaptive	64
abstract_inverted_index.state-of-the-art	169
abstract_inverted_index.Parameter-Efficient	53
cited_by_percentile_year.max	97
cited_by_percentile_year.min	96
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile.value	0.90012642
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True