DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning Article Swipe
Huiping Zhuang
,
Run He
,
Kai Tong
,
Ziqian Zeng
,
Cen Chen
,
Zhiping Lin
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.17503
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.17503
Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper, to solve the exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains a main stream offering an analytical (i.e., closed-form) linear solution, and a compensation stream improving the inherent under-fitting limitation due to adopting linear mapping. The main stream redefines the CIL problem into a Concatenated Recursive Least Squares (C-RLS) task, allowing an equivalence between the CIL and its joint-learning counterpart. The compensation stream is governed by a Dual-Activation Compensation (DAC) module. This module re-activates the embedding with a different activation function from the main stream one, and seeks fitting compensation by projecting the embedding to the null space of the main stream's linear mapping. Empirical results demonstrate that the DS-AL, despite being an exemplar-free technique, delivers performance comparable with or better than that of replay-based methods across various datasets, including CIFAR-100, ImageNet-100 and ImageNet-Full. Additionally, the C-RLS' equivalent property allows the DS-AL to execute CIL in a phase-invariant manner. This is evidenced by a never-before-seen 500-phase CIL ImageNet task, which performs on a level identical to a 5-phase one. Our codes are available at https://github.com/ZHUANGHP/Analytic-continual-learning.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.17503
- https://arxiv.org/pdf/2403.17503
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4393247841
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4393247841Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.17503Digital Object Identifier
- Title
-
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-26Full publication date if available
- Authors
-
Huiping Zhuang, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Zhiping LinList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.17503Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.17503Direct 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/2403.17503Direct OA link when available
- Concepts
-
Dual (grammatical number), Class (philosophy), Computer science, Artificial intelligence, Machine learning, Psychology, Philosophy, LinguisticsTop 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/W4393247841 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.17503 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.17503 |
| ids.openalex | https://openalex.org/W4393247841 |
| fwci | |
| type | preprint |
| title | DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free 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 | 0.9544000029563904 |
| 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 | 0.9351999759674072 |
| 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 |
| topics[2].id | https://openalex.org/T11652 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9269999861717224 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Imbalanced Data Classification Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780980858 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6918975710868835 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q110022 |
| concepts[0].display_name | Dual (grammatical number) |
| concepts[1].id | https://openalex.org/C2777212361 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6480129361152649 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[1].display_name | Class (philosophy) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.4673376977443695 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.45808613300323486 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.35036689043045044 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C15744967 |
| concepts[5].level | 0 |
| concepts[5].score | 0.3470969796180725 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[5].display_name | Psychology |
| concepts[6].id | https://openalex.org/C138885662 |
| concepts[6].level | 0 |
| concepts[6].score | 0.09406059980392456 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[6].display_name | Philosophy |
| concepts[7].id | https://openalex.org/C41895202 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0623336136341095 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[7].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/dual |
| keywords[0].score | 0.6918975710868835 |
| keywords[0].display_name | Dual (grammatical number) |
| keywords[1].id | https://openalex.org/keywords/class |
| keywords[1].score | 0.6480129361152649 |
| keywords[1].display_name | Class (philosophy) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.4673376977443695 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.45808613300323486 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.35036689043045044 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/psychology |
| keywords[5].score | 0.3470969796180725 |
| keywords[5].display_name | Psychology |
| keywords[6].id | https://openalex.org/keywords/philosophy |
| keywords[6].score | 0.09406059980392456 |
| keywords[6].display_name | Philosophy |
| keywords[7].id | https://openalex.org/keywords/linguistics |
| keywords[7].score | 0.0623336136341095 |
| keywords[7].display_name | Linguistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.17503 |
| 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/2403.17503 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2403.17503 |
| locations[1].id | doi:10.48550/arxiv.2403.17503 |
| 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.2403.17503 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5061256037 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4612-5445 |
| authorships[0].author.display_name | Huiping Zhuang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhuang, Huiping |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100521875 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Run He |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | He, Run |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102018972 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8336-1287 |
| authorships[2].author.display_name | Kai Tong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tong, Kai |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5101403806 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0060-7956 |
| authorships[3].author.display_name | Ziqian Zeng |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zeng, Ziqian |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100622590 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1389-0148 |
| authorships[4].author.display_name | Cen Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Chen, Cen |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5049506273 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-1587-1226 |
| authorships[5].author.display_name | Zhiping Lin |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Lin, Zhiping |
| 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/2403.17503 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free 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 | 0.9544000029563904 |
| 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 |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W3107602296, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W4283697347, https://openalex.org/W4210805261 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.17503 |
| 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/2403.17503 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2403.17503 |
| primary_location.id | pmh:oai:arXiv.org:2403.17503 |
| 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/2403.17503 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2403.17503 |
| publication_date | 2024-03-26 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 9, 46, 55, 66, 87, 110, 121, 190, 197, 206, 210 |
| abstract_inverted_index.In | 35 |
| abstract_inverted_index.an | 4, 59, 95, 156 |
| abstract_inverted_index.at | 217 |
| abstract_inverted_index.by | 109, 134, 196 |
| abstract_inverted_index.in | 189 |
| abstract_inverted_index.is | 107, 194 |
| abstract_inverted_index.of | 142, 167 |
| abstract_inverted_index.on | 205 |
| abstract_inverted_index.or | 163 |
| abstract_inverted_index.so | 25 |
| abstract_inverted_index.to | 15, 20, 32, 38, 75, 138, 186, 209 |
| abstract_inverted_index.we | 44 |
| abstract_inverted_index.CIL | 42, 84, 99, 188, 200 |
| abstract_inverted_index.Our | 213 |
| abstract_inverted_index.The | 52, 79, 104 |
| abstract_inverted_index.and | 65, 100, 130, 176 |
| abstract_inverted_index.are | 18, 215 |
| abstract_inverted_index.due | 74 |
| abstract_inverted_index.far | 23 |
| abstract_inverted_index.has | 7 |
| abstract_inverted_index.its | 101 |
| abstract_inverted_index.the | 40, 70, 83, 98, 118, 126, 136, 139, 143, 152, 179, 184 |
| abstract_inverted_index.This | 115, 193 |
| abstract_inverted_index.from | 125 |
| abstract_inverted_index.into | 86 |
| abstract_inverted_index.main | 56, 80, 127, 144 |
| abstract_inverted_index.more | 24 |
| abstract_inverted_index.null | 140 |
| abstract_inverted_index.one, | 129 |
| abstract_inverted_index.one. | 212 |
| abstract_inverted_index.past | 33 |
| abstract_inverted_index.than | 26, 165 |
| abstract_inverted_index.that | 29, 151, 166 |
| abstract_inverted_index.this | 16, 36 |
| abstract_inverted_index.with | 120, 162 |
| abstract_inverted_index.(CIL) | 2 |
| abstract_inverted_index.(DAC) | 113 |
| abstract_inverted_index.DS-AL | 53, 185 |
| abstract_inverted_index.Least | 90 |
| abstract_inverted_index.being | 155 |
| abstract_inverted_index.codes | 214 |
| abstract_inverted_index.level | 207 |
| abstract_inverted_index.prone | 19 |
| abstract_inverted_index.seeks | 131 |
| abstract_inverted_index.solve | 39 |
| abstract_inverted_index.space | 141 |
| abstract_inverted_index.task, | 93, 202 |
| abstract_inverted_index.under | 3 |
| abstract_inverted_index.which | 203 |
| abstract_inverted_index.(i.e., | 61 |
| abstract_inverted_index.C-RLS' | 180 |
| abstract_inverted_index.DS-AL, | 153 |
| abstract_inverted_index.access | 31 |
| abstract_inverted_index.across | 170 |
| abstract_inverted_index.allows | 183 |
| abstract_inverted_index.better | 164 |
| abstract_inverted_index.linear | 63, 77, 146 |
| abstract_inverted_index.module | 116 |
| abstract_inverted_index.paper, | 37 |
| abstract_inverted_index.retain | 30 |
| abstract_inverted_index.stream | 57, 68, 81, 106, 128 |
| abstract_inverted_index.(C-RLS) | 92 |
| abstract_inverted_index.(DS-AL) | 50 |
| abstract_inverted_index.5-phase | 211 |
| abstract_inverted_index.Squares | 91 |
| abstract_inverted_index.between | 97 |
| abstract_inverted_index.despite | 154 |
| abstract_inverted_index.execute | 187 |
| abstract_inverted_index.fitting | 132 |
| abstract_inverted_index.manner. | 192 |
| abstract_inverted_index.methods | 13, 169 |
| abstract_inverted_index.module. | 114 |
| abstract_inverted_index.problem | 85 |
| abstract_inverted_index.propose | 45 |
| abstract_inverted_index.results | 149 |
| abstract_inverted_index.various | 171 |
| abstract_inverted_index.Analytic | 48 |
| abstract_inverted_index.Existing | 12 |
| abstract_inverted_index.ImageNet | 201 |
| abstract_inverted_index.Learning | 49 |
| abstract_inverted_index.adhering | 14 |
| abstract_inverted_index.adopting | 76 |
| abstract_inverted_index.allowing | 94 |
| abstract_inverted_index.contains | 54 |
| abstract_inverted_index.delivers | 159 |
| abstract_inverted_index.function | 124 |
| abstract_inverted_index.governed | 108 |
| abstract_inverted_index.inherent | 71 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.mapping. | 78, 147 |
| abstract_inverted_index.offering | 58 |
| abstract_inverted_index.performs | 204 |
| abstract_inverted_index.problem, | 43 |
| abstract_inverted_index.property | 182 |
| abstract_inverted_index.samples. | 34 |
| abstract_inverted_index.stream's | 145 |
| abstract_inverted_index.500-phase | 199 |
| abstract_inverted_index.Empirical | 148 |
| abstract_inverted_index.Recursive | 89 |
| abstract_inverted_index.approach. | 51 |
| abstract_inverted_index.available | 216 |
| abstract_inverted_index.datasets, | 172 |
| abstract_inverted_index.different | 122 |
| abstract_inverted_index.embedding | 119, 137 |
| abstract_inverted_index.evidenced | 195 |
| abstract_inverted_index.identical | 208 |
| abstract_inverted_index.improving | 69 |
| abstract_inverted_index.including | 173 |
| abstract_inverted_index.presented | 8 |
| abstract_inverted_index.redefines | 82 |
| abstract_inverted_index.solution, | 64 |
| abstract_inverted_index.CIFAR-100, | 174 |
| abstract_inverted_index.activation | 123 |
| abstract_inverted_index.analytical | 60 |
| abstract_inverted_index.challenge. | 11 |
| abstract_inverted_index.comparable | 161 |
| abstract_inverted_index.constraint | 6, 17 |
| abstract_inverted_index.equivalent | 181 |
| abstract_inverted_index.limitation | 73 |
| abstract_inverted_index.projecting | 135 |
| abstract_inverted_index.technique, | 158 |
| abstract_inverted_index.techniques | 28 |
| abstract_inverted_index.Dual-Stream | 47 |
| abstract_inverted_index.demonstrate | 150 |
| abstract_inverted_index.equivalence | 96 |
| abstract_inverted_index.forgetting, | 22 |
| abstract_inverted_index.performance | 160 |
| abstract_inverted_index.significant | 10 |
| abstract_inverted_index.Compensation | 112 |
| abstract_inverted_index.Concatenated | 88 |
| abstract_inverted_index.ImageNet-100 | 175 |
| abstract_inverted_index.catastrophic | 21 |
| abstract_inverted_index.closed-form) | 62 |
| abstract_inverted_index.compensation | 67, 105, 133 |
| abstract_inverted_index.counterpart. | 103 |
| abstract_inverted_index.re-activates | 117 |
| abstract_inverted_index.replay-based | 27, 168 |
| abstract_inverted_index.Additionally, | 178 |
| abstract_inverted_index.exemplar-free | 5, 41, 157 |
| abstract_inverted_index.under-fitting | 72 |
| abstract_inverted_index.ImageNet-Full. | 177 |
| abstract_inverted_index.joint-learning | 102 |
| abstract_inverted_index.Dual-Activation | 111 |
| abstract_inverted_index.phase-invariant | 191 |
| abstract_inverted_index.Class-incremental | 0 |
| abstract_inverted_index.never-before-seen | 198 |
| abstract_inverted_index.https://github.com/ZHUANGHP/Analytic-continual-learning. | 218 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |