Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning Article Swipe
Songlin Dong
,
Yuhang He
,
Zhengdong Zhou
,
Haoyu Luo
,
Xing Wei
,
Alex C. Kot
,
Yihong Gong
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.00515
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2503.00515
Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper focuses on the challenging yet practical multi-label class-incremental learning (MLCIL) problem. In addition to the challenge of catastrophic forgetting, MLCIL encounters issues related to feature confusion, encompassing inter-session and intra-feature confusion. To address these problems, we propose a novel MLCIL approach called class-independent increment (CLIN). Specifically, in contrast to existing methods that extract image-level features, we propose a class-independent incremental network (CINet) to extract multiple class-level embeddings for multi-label samples. It learns and preserves the knowledge of different classes by constructing class-specific tokens. On this basis, we develop two novel loss functions, optimizing the learning of class-specific tokens and class-level embeddings, respectively. These losses aim to distinguish between new and old classes, further alleviating the problem of feature confusion. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on various MLCIL tasks.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2503.00515
- https://arxiv.org/pdf/2503.00515
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415082178
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415082178Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2503.00515Digital Object Identifier
- Title
-
Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-03-01Full publication date if available
- Authors
-
Songlin Dong, Yuhang He, Zhengdong Zhou, Haoyu Luo, Xing Wei, Alex C. Kot, Yihong GongList of authors in order
- Landing page
-
https://arxiv.org/abs/2503.00515Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2503.00515Direct 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/2503.00515Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415082178 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2503.00515 |
| ids.doi | https://doi.org/10.48550/arxiv.2503.00515 |
| ids.openalex | https://openalex.org/W4415082178 |
| fwci | |
| type | preprint |
| title | Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11550 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9193999767303467 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Text and Document Classification Technologies |
| topics[1].id | https://openalex.org/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9153000116348267 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Domain Adaptation and Few-Shot Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2503.00515 |
| 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/2503.00515 |
| 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/2503.00515 |
| locations[1].id | doi:10.48550/arxiv.2503.00515 |
| 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.2503.00515 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5052418585 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7854-3417 |
| authorships[0].author.display_name | Songlin Dong |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dong, Songlin |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5102819064 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6750-1403 |
| authorships[1].author.display_name | Yuhang He |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | He, Yuhang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101629775 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1277-9782 |
| authorships[2].author.display_name | Zhengdong Zhou |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhou, Zhengdong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100641952 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3201-4963 |
| authorships[3].author.display_name | Haoyu Luo |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Luo, Haoyu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100365505 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-7504-2964 |
| authorships[4].author.display_name | Xing Wei |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wei, Xing |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5080977911 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-6262-8125 |
| authorships[5].author.display_name | Alex C. Kot |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Kot, Alex C. |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100687952 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-1793-5836 |
| authorships[6].author.display_name | Yihong Gong |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Gong, Yihong |
| authorships[6].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/2503.00515 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-12T00:00:00 |
| display_name | Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11550 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9193999767303467 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Text and Document Classification Technologies |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2503.00515 |
| 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/2503.00515 |
| 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/2503.00515 |
| primary_location.id | pmh:oai:arXiv.org:2503.00515 |
| 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/2503.00515 |
| 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/2503.00515 |
| publication_date | 2025-03-01 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 65, 85 |
| abstract_inverted_index.In | 39 |
| abstract_inverted_index.It | 98 |
| abstract_inverted_index.On | 111 |
| abstract_inverted_index.To | 59 |
| abstract_inverted_index.as | 19 |
| abstract_inverted_index.by | 107 |
| abstract_inverted_index.in | 74 |
| abstract_inverted_index.of | 44, 104, 123, 144, 158 |
| abstract_inverted_index.on | 2, 7, 29, 149, 168 |
| abstract_inverted_index.to | 41, 51, 76, 90, 133 |
| abstract_inverted_index.we | 63, 83, 114 |
| abstract_inverted_index.VOC | 153 |
| abstract_inverted_index.aim | 132 |
| abstract_inverted_index.and | 22, 56, 100, 126, 137, 151, 165 |
| abstract_inverted_index.for | 95, 161 |
| abstract_inverted_index.new | 136 |
| abstract_inverted_index.old | 138 |
| abstract_inverted_index.our | 159 |
| abstract_inverted_index.the | 30, 42, 102, 121, 142, 156 |
| abstract_inverted_index.two | 116 |
| abstract_inverted_index.yet | 32 |
| abstract_inverted_index.loss | 118 |
| abstract_inverted_index.such | 18 |
| abstract_inverted_index.that | 79 |
| abstract_inverted_index.this | 26, 112 |
| abstract_inverted_index.MLCIL | 47, 67, 170 |
| abstract_inverted_index.These | 130 |
| abstract_inverted_index.image | 20 |
| abstract_inverted_index.novel | 66, 117 |
| abstract_inverted_index.often | 14 |
| abstract_inverted_index.paper | 27 |
| abstract_inverted_index.these | 61 |
| abstract_inverted_index.PASCAL | 152 |
| abstract_inverted_index.basis, | 113 |
| abstract_inverted_index.called | 69 |
| abstract_inverted_index.issues | 49 |
| abstract_inverted_index.learns | 99 |
| abstract_inverted_index.losses | 131 |
| abstract_inverted_index.method | 160 |
| abstract_inverted_index.tasks. | 10, 171 |
| abstract_inverted_index.tokens | 125 |
| abstract_inverted_index.(CINet) | 89 |
| abstract_inverted_index.(CLIN). | 72 |
| abstract_inverted_index.(MLCIL) | 37 |
| abstract_inverted_index.Current | 0 |
| abstract_inverted_index.MS-COCO | 150 |
| abstract_inverted_index.address | 60 |
| abstract_inverted_index.between | 135 |
| abstract_inverted_index.classes | 106 |
| abstract_inverted_index.develop | 115 |
| abstract_inverted_index.extract | 80, 91 |
| abstract_inverted_index.feature | 52, 145 |
| abstract_inverted_index.focuses | 6, 28 |
| abstract_inverted_index.further | 140 |
| abstract_inverted_index.involve | 15 |
| abstract_inverted_index.medical | 23 |
| abstract_inverted_index.methods | 78 |
| abstract_inverted_index.network | 88 |
| abstract_inverted_index.problem | 143 |
| abstract_inverted_index.propose | 64, 84 |
| abstract_inverted_index.related | 50 |
| abstract_inverted_index.tokens. | 110 |
| abstract_inverted_index.various | 169 |
| abstract_inverted_index.However, | 11 |
| abstract_inverted_index.addition | 40 |
| abstract_inverted_index.approach | 68 |
| abstract_inverted_index.classes, | 139 |
| abstract_inverted_index.contrast | 75 |
| abstract_inverted_index.datasets | 154 |
| abstract_inverted_index.existing | 77 |
| abstract_inverted_index.imaging. | 24 |
| abstract_inverted_index.learning | 4, 36, 122 |
| abstract_inverted_index.multiple | 92 |
| abstract_inverted_index.problem. | 38 |
| abstract_inverted_index.research | 1 |
| abstract_inverted_index.samples. | 97 |
| abstract_inverted_index.Extensive | 147 |
| abstract_inverted_index.challenge | 43 |
| abstract_inverted_index.different | 105 |
| abstract_inverted_index.features, | 82 |
| abstract_inverted_index.improving | 162 |
| abstract_inverted_index.increment | 71 |
| abstract_inverted_index.knowledge | 103 |
| abstract_inverted_index.practical | 33 |
| abstract_inverted_index.preserves | 101 |
| abstract_inverted_index.primarily | 5 |
| abstract_inverted_index.problems, | 62 |
| abstract_inverted_index.retrieval | 21 |
| abstract_inverted_index.Therefore, | 25 |
| abstract_inverted_index.confusion, | 53 |
| abstract_inverted_index.confusion. | 58, 146 |
| abstract_inverted_index.embeddings | 94 |
| abstract_inverted_index.encounters | 48 |
| abstract_inverted_index.forgetting | 167 |
| abstract_inverted_index.functions, | 119 |
| abstract_inverted_index.mitigating | 166 |
| abstract_inverted_index.optimizing | 120 |
| abstract_inverted_index.real-world | 12 |
| abstract_inverted_index.scenarios, | 17 |
| abstract_inverted_index.alleviating | 141 |
| abstract_inverted_index.challenging | 31 |
| abstract_inverted_index.class-level | 93, 127 |
| abstract_inverted_index.demonstrate | 155 |
| abstract_inverted_index.distinguish | 134 |
| abstract_inverted_index.embeddings, | 128 |
| abstract_inverted_index.experiments | 148 |
| abstract_inverted_index.forgetting, | 46 |
| abstract_inverted_index.image-level | 81 |
| abstract_inverted_index.incremental | 87 |
| abstract_inverted_index.multi-label | 16, 34, 96 |
| abstract_inverted_index.performance | 164 |
| abstract_inverted_index.recognition | 163 |
| abstract_inverted_index.applications | 13 |
| abstract_inverted_index.catastrophic | 45 |
| abstract_inverted_index.constructing | 108 |
| abstract_inverted_index.encompassing | 54 |
| abstract_inverted_index.single-label | 8 |
| abstract_inverted_index.Specifically, | 73 |
| abstract_inverted_index.effectiveness | 157 |
| abstract_inverted_index.inter-session | 55 |
| abstract_inverted_index.intra-feature | 57 |
| abstract_inverted_index.respectively. | 129 |
| abstract_inverted_index.class-specific | 109, 124 |
| abstract_inverted_index.classification | 9 |
| abstract_inverted_index.class-incremental | 3, 35 |
| abstract_inverted_index.class-independent | 70, 86 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |