Knowledge Restore and Transfer for Multi-label Class-Incremental Learning Article Swipe
Songlin Dong
,
Haoyu Luo
,
Yuhang He
,
Xing Wei Yihong Gong
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.13334
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.13334
Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic forgetting in class-incremental learning, these methods have difficulty in solving the MLCIL problem due to label absence and information dilution. In this paper, we propose a knowledge restore and transfer (KRT) framework for MLCIL, which includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Besides, we propose a token loss to jointly optimize the incremental cross-attention module. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on multi-label class-incremental learning tasks.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2302.13334
- https://arxiv.org/pdf/2302.13334
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4322716931
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4322716931Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2302.13334Digital Object Identifier
- Title
-
Knowledge Restore and Transfer for Multi-label Class-Incremental LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-02-26Full publication date if available
- Authors
-
Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei Yihong GongList of authors in order
- Landing page
-
https://arxiv.org/abs/2302.13334Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2302.13334Direct 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/2302.13334Direct OA link when available
- Concepts
-
Forgetting, Computer science, Incremental learning, Pascal (unit), Artificial intelligence, Class (philosophy), Machine learning, Transfer of learning, Linguistics, Philosophy, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4322716931 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2302.13334 |
| ids.doi | https://doi.org/10.48550/arxiv.2302.13334 |
| ids.openalex | https://openalex.org/W4322716931 |
| fwci | |
| type | preprint |
| title | Knowledge Restore and Transfer for Multi-label Class-Incremental Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11307 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9889000058174133 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[1].id | https://openalex.org/T11550 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9811999797821045 |
| 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 | Text and Document Classification Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C7149132 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8737698793411255 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1377840 |
| concepts[0].display_name | Forgetting |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7481920719146729 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2780735816 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7267643213272095 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q28324931 |
| concepts[2].display_name | Incremental learning |
| concepts[3].id | https://openalex.org/C75608658 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6242382526397705 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q44395 |
| concepts[3].display_name | Pascal (unit) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.6049351096153259 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2777212361 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5985409021377563 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[5].display_name | Class (philosophy) |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5822217464447021 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C150899416 |
| concepts[7].level | 2 |
| concepts[7].score | 0.49322956800460815 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1820378 |
| concepts[7].display_name | Transfer of learning |
| concepts[8].id | https://openalex.org/C41895202 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[8].display_name | Linguistics |
| concepts[9].id | https://openalex.org/C138885662 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[9].display_name | Philosophy |
| concepts[10].id | https://openalex.org/C199360897 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[10].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/forgetting |
| keywords[0].score | 0.8737698793411255 |
| keywords[0].display_name | Forgetting |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7481920719146729 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/incremental-learning |
| keywords[2].score | 0.7267643213272095 |
| keywords[2].display_name | Incremental learning |
| keywords[3].id | https://openalex.org/keywords/pascal |
| keywords[3].score | 0.6242382526397705 |
| keywords[3].display_name | Pascal (unit) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.6049351096153259 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/class |
| keywords[5].score | 0.5985409021377563 |
| keywords[5].display_name | Class (philosophy) |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.5822217464447021 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/transfer-of-learning |
| keywords[7].score | 0.49322956800460815 |
| keywords[7].display_name | Transfer of learning |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2302.13334 |
| 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/2302.13334 |
| 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/2302.13334 |
| locations[1].id | doi:10.48550/arxiv.2302.13334 |
| 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.2302.13334 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5043783105 |
| authorships[0].author.orcid | |
| 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/A5100641952 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3201-4963 |
| authorships[1].author.display_name | Haoyu Luo |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Luo, Haoyu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5115467762 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Yuhang He |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | He, Yuhang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5071327005 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xing Wei Yihong Gong |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Gong, Xing Wei Yihong |
| authorships[3].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://arxiv.org/pdf/2302.13334 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-03-03T00:00:00 |
| display_name | Knowledge Restore and Transfer 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/T11307 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9889000058174133 |
| 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 | Domain Adaptation and Few-Shot Learning |
| related_works | https://openalex.org/W4287067590, https://openalex.org/W3186262193, https://openalex.org/W3192176272, https://openalex.org/W4391158518, https://openalex.org/W4297634446, https://openalex.org/W4381322349, https://openalex.org/W3085307110, https://openalex.org/W3157400488, https://openalex.org/W4382021137, https://openalex.org/W3009921798 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2302.13334 |
| 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/2302.13334 |
| 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/2302.13334 |
| primary_location.id | pmh:oai:arXiv.org:2302.13334 |
| 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/2302.13334 |
| 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/2302.13334 |
| publication_date | 2023-02-26 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 61, 72, 105 |
| abstract_inverted_index.In | 56 |
| abstract_inverted_index.an | 84 |
| abstract_inverted_index.in | 37, 44 |
| abstract_inverted_index.is | 20 |
| abstract_inverted_index.of | 34, 126 |
| abstract_inverted_index.on | 6, 117, 136 |
| abstract_inverted_index.to | 30, 50, 77, 88, 97, 108 |
| abstract_inverted_index.we | 59, 103 |
| abstract_inverted_index.VOC | 121 |
| abstract_inverted_index.and | 53, 64, 83, 92, 119, 133 |
| abstract_inverted_index.due | 49 |
| abstract_inverted_index.for | 68, 129 |
| abstract_inverted_index.new | 99 |
| abstract_inverted_index.old | 80, 94 |
| abstract_inverted_index.our | 127 |
| abstract_inverted_index.the | 32, 46, 79, 98, 111, 124 |
| abstract_inverted_index.been | 26 |
| abstract_inverted_index.have | 25, 42 |
| abstract_inverted_index.loss | 107 |
| abstract_inverted_index.many | 27 |
| abstract_inverted_index.more | 16 |
| abstract_inverted_index.save | 89 |
| abstract_inverted_index.this | 57 |
| abstract_inverted_index.with | 15 |
| abstract_inverted_index.(DPL) | 75 |
| abstract_inverted_index.(KRT) | 66 |
| abstract_inverted_index.MLCIL | 47 |
| abstract_inverted_index.class | 81, 95 |
| abstract_inverted_index.label | 51 |
| abstract_inverted_index.model | 100 |
| abstract_inverted_index.solve | 31 |
| abstract_inverted_index.tasks | 9 |
| abstract_inverted_index.there | 24 |
| abstract_inverted_index.these | 40 |
| abstract_inverted_index.token | 106 |
| abstract_inverted_index.which | 70 |
| abstract_inverted_index.while | 10 |
| abstract_inverted_index.MLCIL, | 69 |
| abstract_inverted_index.PASCAL | 120 |
| abstract_inverted_index.mainly | 4 |
| abstract_inverted_index.method | 128 |
| abstract_inverted_index.module | 76, 87 |
| abstract_inverted_index.paper, | 58 |
| abstract_inverted_index.rarely | 21 |
| abstract_inverted_index.tasks. | 140 |
| abstract_inverted_index.(MLCIL) | 14 |
| abstract_inverted_index.Current | 0 |
| abstract_inverted_index.MS-COCO | 118 |
| abstract_inverted_index.absence | 52 |
| abstract_inverted_index.dynamic | 73 |
| abstract_inverted_index.focuses | 5 |
| abstract_inverted_index.jointly | 109 |
| abstract_inverted_index.methods | 29, 41 |
| abstract_inverted_index.module. | 114 |
| abstract_inverted_index.problem | 33, 48 |
| abstract_inverted_index.propose | 60, 104 |
| abstract_inverted_index.restore | 63, 78 |
| abstract_inverted_index.results | 116 |
| abstract_inverted_index.solving | 45 |
| abstract_inverted_index.Although | 23 |
| abstract_inverted_index.Besides, | 102 |
| abstract_inverted_index.datasets | 122 |
| abstract_inverted_index.includes | 71 |
| abstract_inverted_index.learning | 2, 13, 139 |
| abstract_inverted_index.optimize | 110 |
| abstract_inverted_index.research | 3 |
| abstract_inverted_index.studied. | 22 |
| abstract_inverted_index.transfer | 65, 93 |
| abstract_inverted_index.dilution. | 55 |
| abstract_inverted_index.framework | 67 |
| abstract_inverted_index.improving | 130 |
| abstract_inverted_index.knowledge | 62, 82, 91, 96 |
| abstract_inverted_index.learning, | 39 |
| abstract_inverted_index.practical | 17 |
| abstract_inverted_index.scenarios | 19 |
| abstract_inverted_index.difficulty | 43 |
| abstract_inverted_index.forgetting | 36, 135 |
| abstract_inverted_index.mitigating | 134 |
| abstract_inverted_index.application | 18 |
| abstract_inverted_index.demonstrate | 123 |
| abstract_inverted_index.incremental | 85, 112 |
| abstract_inverted_index.information | 54 |
| abstract_inverted_index.multi-label | 11, 137 |
| abstract_inverted_index.performance | 132 |
| abstract_inverted_index.recognition | 131 |
| abstract_inverted_index.Experimental | 115 |
| abstract_inverted_index.catastrophic | 35 |
| abstract_inverted_index.pseudo-label | 74 |
| abstract_inverted_index.single-label | 7 |
| abstract_inverted_index.effectiveness | 125 |
| abstract_inverted_index.sufficiently. | 101 |
| abstract_inverted_index.classification | 8 |
| abstract_inverted_index.anti-forgetting | 28 |
| abstract_inverted_index.cross-attention | 113 |
| abstract_inverted_index.session-specific | 90 |
| abstract_inverted_index.class-incremental | 1, 12, 38, 138 |
| abstract_inverted_index.cross-attention(ICA) | 86 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |