Analytic Continual Test-Time Adaptation for Multi-Modality Corruption Article Swipe
Yufei Zhang
,
Y. C. Xu
,
Hongxin Wei
,
Zhiping Lin
,
Huiping Zhuang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.22373
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2410.22373
Test-Time Adaptation (TTA) enables pre-trained models to bridge the gap between source and target datasets using unlabeled test data, addressing domain shifts caused by corruptions like weather changes, noise, or sensor malfunctions in test time. Multi-Modal Continual Test-Time Adaptation (MM-CTTA), as an extension of standard TTA, further allows models to handle multi-modal inputs and adapt to continuously evolving target domains. However, MM-CTTA faces critical challenges such as catastrophic forgetting and reliability bias, which are rarely addressed effectively under multi-modal corruption scenarios. In this paper, we propose a novel approach, Multi-modality Dynamic Analytic Adapter (MDAA), to tackle MM-CTTA tasks. MDAA introduces analytic learning,a closed-form training technique,through Analytic Classifiers (ACs) to mitigate catastrophic forgetting. Furthermore, we design the Dynamic Late Fusion Mechanism (DLFM) to dynamically select and integrate reliable information from different modalities. Extensive experiments show that MDAA achieves state-of-the-art performance across the proposed tasks.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2410.22373
- https://arxiv.org/pdf/2410.22373
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404342179
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404342179Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2410.22373Digital Object Identifier
- Title
-
Analytic Continual Test-Time Adaptation for Multi-Modality CorruptionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-29Full publication date if available
- Authors
-
Yufei Zhang, Y. C. Xu, Hongxin Wei, Zhiping Lin, Huiping ZhuangList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.22373Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.22373Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2410.22373Direct OA link when available
- Concepts
-
Modality (human–computer interaction), Adaptation (eye), Test (biology), Language change, Computer science, Cognitive psychology, Psychology, Artificial intelligence, Neuroscience, Geology, Linguistics, Philosophy, PaleontologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4404342179 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2410.22373 |
| ids.doi | https://doi.org/10.48550/arxiv.2410.22373 |
| ids.openalex | https://openalex.org/W4404342179 |
| fwci | |
| type | preprint |
| title | Analytic Continual Test-Time Adaptation for Multi-Modality Corruption |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12169 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9350000023841858 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2210 |
| topics[0].subfield.display_name | Mechanical Engineering |
| topics[0].display_name | Non-Destructive Testing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780226545 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7270280718803406 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6888030 |
| concepts[0].display_name | Modality (human–computer interaction) |
| concepts[1].id | https://openalex.org/C139807058 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6738505363464355 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q352374 |
| concepts[1].display_name | Adaptation (eye) |
| concepts[2].id | https://openalex.org/C2777267654 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6101860404014587 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3519023 |
| concepts[2].display_name | Test (biology) |
| concepts[3].id | https://openalex.org/C2780027415 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5769067406654358 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q524648 |
| concepts[3].display_name | Language change |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.41985028982162476 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C180747234 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3344419002532959 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[5].display_name | Cognitive psychology |
| concepts[6].id | https://openalex.org/C15744967 |
| concepts[6].level | 0 |
| concepts[6].score | 0.32807981967926025 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[6].display_name | Psychology |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.27275770902633667 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C169760540 |
| concepts[8].level | 1 |
| concepts[8].score | 0.08404380083084106 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[8].display_name | Neuroscience |
| concepts[9].id | https://openalex.org/C127313418 |
| concepts[9].level | 0 |
| concepts[9].score | 0.07375991344451904 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[9].display_name | Geology |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.06500664353370667 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.060026615858078 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C151730666 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[12].display_name | Paleontology |
| keywords[0].id | https://openalex.org/keywords/modality |
| keywords[0].score | 0.7270280718803406 |
| keywords[0].display_name | Modality (human–computer interaction) |
| keywords[1].id | https://openalex.org/keywords/adaptation |
| keywords[1].score | 0.6738505363464355 |
| keywords[1].display_name | Adaptation (eye) |
| keywords[2].id | https://openalex.org/keywords/test |
| keywords[2].score | 0.6101860404014587 |
| keywords[2].display_name | Test (biology) |
| keywords[3].id | https://openalex.org/keywords/language-change |
| keywords[3].score | 0.5769067406654358 |
| keywords[3].display_name | Language change |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.41985028982162476 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[5].score | 0.3344419002532959 |
| keywords[5].display_name | Cognitive psychology |
| keywords[6].id | https://openalex.org/keywords/psychology |
| keywords[6].score | 0.32807981967926025 |
| keywords[6].display_name | Psychology |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.27275770902633667 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/neuroscience |
| keywords[8].score | 0.08404380083084106 |
| keywords[8].display_name | Neuroscience |
| keywords[9].id | https://openalex.org/keywords/geology |
| keywords[9].score | 0.07375991344451904 |
| keywords[9].display_name | Geology |
| keywords[10].id | https://openalex.org/keywords/linguistics |
| keywords[10].score | 0.06500664353370667 |
| keywords[10].display_name | Linguistics |
| keywords[11].id | https://openalex.org/keywords/philosophy |
| keywords[11].score | 0.060026615858078 |
| keywords[11].display_name | Philosophy |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2410.22373 |
| 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/2410.22373 |
| 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/2410.22373 |
| locations[1].id | doi:10.48550/arxiv.2410.22373 |
| 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.2410.22373 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5115594297 |
| authorships[0].author.orcid | https://orcid.org/0009-0009-3863-204X |
| authorships[0].author.display_name | Yufei Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhang, Yufei |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100591919 |
| authorships[1].author.orcid | https://orcid.org/0009-0007-7340-7871 |
| authorships[1].author.display_name | Y. C. Xu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xu, Yicheng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5020027500 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8973-2843 |
| authorships[2].author.display_name | Hongxin Wei |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wei, Hongxin |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5049506273 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1587-1226 |
| authorships[3].author.display_name | Zhiping Lin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lin, Zhiping |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5061256037 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4612-5445 |
| authorships[4].author.display_name | Huiping Zhuang |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Zhuang, Huiping |
| 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/2410.22373 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Analytic Continual Test-Time Adaptation for Multi-Modality Corruption |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12169 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9350000023841858 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2210 |
| primary_topic.subfield.display_name | Mechanical Engineering |
| primary_topic.display_name | Non-Destructive Testing Techniques |
| related_works | https://openalex.org/W2385859805, https://openalex.org/W2530972254, https://openalex.org/W2997567050, https://openalex.org/W2374013449, https://openalex.org/W73545470, https://openalex.org/W2364381299, https://openalex.org/W2374430585, https://openalex.org/W3144423903, https://openalex.org/W2377397762, https://openalex.org/W2793967660 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.22373 |
| 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/2410.22373 |
| 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/2410.22373 |
| primary_location.id | pmh:oai:arXiv.org:2410.22373 |
| 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/2410.22373 |
| 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/2410.22373 |
| publication_date | 2024-10-29 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 86 |
| abstract_inverted_index.In | 81 |
| abstract_inverted_index.an | 41 |
| abstract_inverted_index.as | 40, 66 |
| abstract_inverted_index.by | 23 |
| abstract_inverted_index.in | 32 |
| abstract_inverted_index.of | 43 |
| abstract_inverted_index.or | 29 |
| abstract_inverted_index.to | 6, 49, 55, 94, 108, 121 |
| abstract_inverted_index.we | 84, 113 |
| abstract_inverted_index.and | 12, 53, 69, 124 |
| abstract_inverted_index.are | 73 |
| abstract_inverted_index.gap | 9 |
| abstract_inverted_index.the | 8, 115, 140 |
| abstract_inverted_index.Late | 117 |
| abstract_inverted_index.MDAA | 98, 135 |
| abstract_inverted_index.TTA, | 45 |
| abstract_inverted_index.from | 128 |
| abstract_inverted_index.like | 25 |
| abstract_inverted_index.show | 133 |
| abstract_inverted_index.such | 65 |
| abstract_inverted_index.test | 17, 33 |
| abstract_inverted_index.that | 134 |
| abstract_inverted_index.this | 82 |
| abstract_inverted_index.(ACs) | 107 |
| abstract_inverted_index.(TTA) | 2 |
| abstract_inverted_index.adapt | 54 |
| abstract_inverted_index.bias, | 71 |
| abstract_inverted_index.data, | 18 |
| abstract_inverted_index.faces | 62 |
| abstract_inverted_index.novel | 87 |
| abstract_inverted_index.time. | 34 |
| abstract_inverted_index.under | 77 |
| abstract_inverted_index.using | 15 |
| abstract_inverted_index.which | 72 |
| abstract_inverted_index.(DLFM) | 120 |
| abstract_inverted_index.Fusion | 118 |
| abstract_inverted_index.across | 139 |
| abstract_inverted_index.allows | 47 |
| abstract_inverted_index.bridge | 7 |
| abstract_inverted_index.caused | 22 |
| abstract_inverted_index.design | 114 |
| abstract_inverted_index.domain | 20 |
| abstract_inverted_index.handle | 50 |
| abstract_inverted_index.inputs | 52 |
| abstract_inverted_index.models | 5, 48 |
| abstract_inverted_index.noise, | 28 |
| abstract_inverted_index.paper, | 83 |
| abstract_inverted_index.rarely | 74 |
| abstract_inverted_index.select | 123 |
| abstract_inverted_index.sensor | 30 |
| abstract_inverted_index.shifts | 21 |
| abstract_inverted_index.source | 11 |
| abstract_inverted_index.tackle | 95 |
| abstract_inverted_index.target | 13, 58 |
| abstract_inverted_index.tasks. | 97, 142 |
| abstract_inverted_index.(MDAA), | 93 |
| abstract_inverted_index.Adapter | 92 |
| abstract_inverted_index.Dynamic | 90, 116 |
| abstract_inverted_index.MM-CTTA | 61, 96 |
| abstract_inverted_index.between | 10 |
| abstract_inverted_index.enables | 3 |
| abstract_inverted_index.further | 46 |
| abstract_inverted_index.propose | 85 |
| abstract_inverted_index.weather | 26 |
| abstract_inverted_index.Analytic | 91, 105 |
| abstract_inverted_index.However, | 60 |
| abstract_inverted_index.achieves | 136 |
| abstract_inverted_index.analytic | 100 |
| abstract_inverted_index.changes, | 27 |
| abstract_inverted_index.critical | 63 |
| abstract_inverted_index.datasets | 14 |
| abstract_inverted_index.domains. | 59 |
| abstract_inverted_index.evolving | 57 |
| abstract_inverted_index.mitigate | 109 |
| abstract_inverted_index.proposed | 141 |
| abstract_inverted_index.reliable | 126 |
| abstract_inverted_index.standard | 44 |
| abstract_inverted_index.training | 103 |
| abstract_inverted_index.Continual | 36 |
| abstract_inverted_index.Extensive | 131 |
| abstract_inverted_index.Mechanism | 119 |
| abstract_inverted_index.Test-Time | 0, 37 |
| abstract_inverted_index.addressed | 75 |
| abstract_inverted_index.approach, | 88 |
| abstract_inverted_index.different | 129 |
| abstract_inverted_index.extension | 42 |
| abstract_inverted_index.integrate | 125 |
| abstract_inverted_index.unlabeled | 16 |
| abstract_inverted_index.(MM-CTTA), | 39 |
| abstract_inverted_index.Adaptation | 1, 38 |
| abstract_inverted_index.addressing | 19 |
| abstract_inverted_index.challenges | 64 |
| abstract_inverted_index.corruption | 79 |
| abstract_inverted_index.forgetting | 68 |
| abstract_inverted_index.introduces | 99 |
| abstract_inverted_index.learning,a | 101 |
| abstract_inverted_index.scenarios. | 80 |
| abstract_inverted_index.Classifiers | 106 |
| abstract_inverted_index.Multi-Modal | 35 |
| abstract_inverted_index.closed-form | 102 |
| abstract_inverted_index.corruptions | 24 |
| abstract_inverted_index.dynamically | 122 |
| abstract_inverted_index.effectively | 76 |
| abstract_inverted_index.experiments | 132 |
| abstract_inverted_index.forgetting. | 111 |
| abstract_inverted_index.information | 127 |
| abstract_inverted_index.modalities. | 130 |
| abstract_inverted_index.multi-modal | 51, 78 |
| abstract_inverted_index.performance | 138 |
| abstract_inverted_index.pre-trained | 4 |
| abstract_inverted_index.reliability | 70 |
| abstract_inverted_index.Furthermore, | 112 |
| abstract_inverted_index.catastrophic | 67, 110 |
| abstract_inverted_index.continuously | 56 |
| abstract_inverted_index.malfunctions | 31 |
| abstract_inverted_index.Multi-modality | 89 |
| abstract_inverted_index.state-of-the-art | 137 |
| abstract_inverted_index.technique,through | 104 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |