Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers Article Swipe
Qi Deng
,
Shuaicheng Niu
,
Ronghao Zhang
,
Yi‐Jen Chen
,
Runhao Zeng
,
Jian Chen
,
Xiping Hu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i15.33783
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i15.33783
Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this optimization process, unsupervised learning objectives like entropy minimization frequently encounter noisy learning signals. These signals produce unreliable gradients, which hinder the model’s ability to converge to an optimal solution quickly and introduce significant instability into the optimization process. In this paper, we seek to resolve these issues from the perspective of optimizer design. Unlike prior TTA using manually designed optimizers like SGD, we employ a learning-to-optimize approach to automatically learn an optimizer, called Meta Gradient Generator (MGG). Specifically, we aim for MGG to effectively utilize historical gradient information during the online optimization process to optimize the current model. To this end, in MGG, we design a lightweight and efficient sequence modeling layer -- gradient memory layer. It exploits a self-supervised reconstruction loss to compress historical gradient information into network parameters, thereby enabling better memorization ability over a long-term adaptation process. We only need a small number of unlabeled samples to pre-train MGG, and then the trained MGG can be deployed to process unseen samples. Promising results on ImageNet-C/R/Sketch/A indicate that our method surpasses current state-of-the-art methods with fewer updates, less data, and significantly shorter adaptation times. Compared with a previous SOTA SAR, we achieve 7.4% accuracy improvement and 4.2x faster adaptation speed on ImageNet-C.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i15.33783
- https://ojs.aaai.org/index.php/AAAI/article/download/33783/35938
- OA Status
- diamond
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409347209
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409347209Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i15.33783Digital Object Identifier
- Title
-
Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training LayersWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Qi Deng, Shuaicheng Niu, Ronghao Zhang, Yi‐Jen Chen, Runhao Zeng, Jian Chen, Xiping HuList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i15.33783Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/33783/35938Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/33783/35938Direct OA link when available
- Concepts
-
Test (biology), Adaptation (eye), Training (meteorology), Computer science, Artificial intelligence, Machine learning, Psychology, Geology, Geography, Meteorology, Paleontology, NeuroscienceTop 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/W4409347209 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i15.33783 |
| ids.doi | https://doi.org/10.1609/aaai.v39i15.33783 |
| ids.openalex | https://openalex.org/W4409347209 |
| fwci | 0.0 |
| type | article |
| title | Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers |
| biblio.issue | 15 |
| biblio.volume | 39 |
| biblio.last_page | 16243 |
| biblio.first_page | 16235 |
| topics[0].id | https://openalex.org/T11206 |
| topics[0].field.id | https://openalex.org/fields/31 |
| topics[0].field.display_name | Physics and Astronomy |
| topics[0].score | 0.8883000016212463 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3109 |
| topics[0].subfield.display_name | Statistical and Nonlinear Physics |
| topics[0].display_name | Model Reduction and Neural Networks |
| 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 | 0.8781999945640564 |
| 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/T10531 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.7901999950408936 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Advanced Vision and Imaging |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2777267654 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6540572643280029 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q3519023 |
| concepts[0].display_name | Test (biology) |
| concepts[1].id | https://openalex.org/C139807058 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6520599126815796 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q352374 |
| concepts[1].display_name | Adaptation (eye) |
| concepts[2].id | https://openalex.org/C2777211547 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5052171349525452 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[2].display_name | Training (meteorology) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5030092597007751 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.36805981397628784 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.33434808254241943 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C15744967 |
| concepts[6].level | 0 |
| concepts[6].score | 0.2663673162460327 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[6].display_name | Psychology |
| concepts[7].id | https://openalex.org/C127313418 |
| concepts[7].level | 0 |
| concepts[7].score | 0.10822740197181702 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[7].display_name | Geology |
| concepts[8].id | https://openalex.org/C205649164 |
| concepts[8].level | 0 |
| concepts[8].score | 0.08318930864334106 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[8].display_name | Geography |
| concepts[9].id | https://openalex.org/C153294291 |
| concepts[9].level | 1 |
| concepts[9].score | 0.08238804340362549 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[9].display_name | Meteorology |
| concepts[10].id | https://openalex.org/C151730666 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[10].display_name | Paleontology |
| concepts[11].id | https://openalex.org/C169760540 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[11].display_name | Neuroscience |
| keywords[0].id | https://openalex.org/keywords/test |
| keywords[0].score | 0.6540572643280029 |
| keywords[0].display_name | Test (biology) |
| keywords[1].id | https://openalex.org/keywords/adaptation |
| keywords[1].score | 0.6520599126815796 |
| keywords[1].display_name | Adaptation (eye) |
| keywords[2].id | https://openalex.org/keywords/training |
| keywords[2].score | 0.5052171349525452 |
| keywords[2].display_name | Training (meteorology) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5030092597007751 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.36805981397628784 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.33434808254241943 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/psychology |
| keywords[6].score | 0.2663673162460327 |
| keywords[6].display_name | Psychology |
| keywords[7].id | https://openalex.org/keywords/geology |
| keywords[7].score | 0.10822740197181702 |
| keywords[7].display_name | Geology |
| keywords[8].id | https://openalex.org/keywords/geography |
| keywords[8].score | 0.08318930864334106 |
| keywords[8].display_name | Geography |
| keywords[9].id | https://openalex.org/keywords/meteorology |
| keywords[9].score | 0.08238804340362549 |
| keywords[9].display_name | Meteorology |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i15.33783 |
| 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/33783/35938 |
| 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.v39i15.33783 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5089086011 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3646-4953 |
| authorships[0].author.display_name | Qi Deng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Qi Deng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5064880801 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8212-1831 |
| authorships[1].author.display_name | Shuaicheng Niu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shuaicheng Niu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5086603059 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Ronghao Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ronghao Zhang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100640230 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5178-2335 |
| authorships[3].author.display_name | Yi‐Jen Chen |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yaofo Chen |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5018498977 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8694-4245 |
| authorships[4].author.display_name | Runhao Zeng |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Runhao Zeng |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101821558 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-9186-0764 |
| authorships[5].author.display_name | Jian Chen |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Jian Chen |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5007941489 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-4952-699X |
| authorships[6].author.display_name | Xiping Hu |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Xiping Hu |
| authorships[6].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/33783/35938 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11206 |
| primary_topic.field.id | https://openalex.org/fields/31 |
| primary_topic.field.display_name | Physics and Astronomy |
| primary_topic.score | 0.8883000016212463 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3109 |
| primary_topic.subfield.display_name | Statistical and Nonlinear Physics |
| primary_topic.display_name | Model Reduction and Neural Networks |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W4387369504, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W4283697347 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i15.33783 |
| 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/33783/35938 |
| 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.v39i15.33783 |
| primary_location.id | doi:10.1609/aaai.v39i15.33783 |
| 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/33783/35938 |
| 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.v39i15.33783 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 96, 137, 150, 168, 175, 220 |
| abstract_inverted_index.-- | 144 |
| abstract_inverted_index.In | 70 |
| abstract_inverted_index.It | 148 |
| abstract_inverted_index.To | 130 |
| abstract_inverted_index.We | 172 |
| abstract_inverted_index.an | 58, 102 |
| abstract_inverted_index.be | 190 |
| abstract_inverted_index.in | 26, 30, 133 |
| abstract_inverted_index.of | 82, 178 |
| abstract_inverted_index.on | 198, 234 |
| abstract_inverted_index.or | 19 |
| abstract_inverted_index.to | 4, 14, 16, 55, 57, 75, 99, 114, 125, 154, 181, 192 |
| abstract_inverted_index.we | 73, 94, 110, 135, 224 |
| abstract_inverted_index.MGG | 113, 188 |
| abstract_inverted_index.TTA | 87 |
| abstract_inverted_index.aim | 111 |
| abstract_inverted_index.and | 62, 139, 184, 213, 229 |
| abstract_inverted_index.can | 189 |
| abstract_inverted_index.for | 112 |
| abstract_inverted_index.new | 17 |
| abstract_inverted_index.our | 202 |
| abstract_inverted_index.the | 52, 67, 80, 121, 127, 186 |
| abstract_inverted_index.4.2x | 230 |
| abstract_inverted_index.7.4% | 226 |
| abstract_inverted_index.MGG, | 134, 183 |
| abstract_inverted_index.Meta | 105 |
| abstract_inverted_index.SAR, | 223 |
| abstract_inverted_index.SGD, | 93 |
| abstract_inverted_index.SOTA | 222 |
| abstract_inverted_index.aims | 3 |
| abstract_inverted_index.data | 13 |
| abstract_inverted_index.end, | 132 |
| abstract_inverted_index.from | 79 |
| abstract_inverted_index.into | 66, 159 |
| abstract_inverted_index.less | 211 |
| abstract_inverted_index.like | 37, 92 |
| abstract_inverted_index.loss | 153 |
| abstract_inverted_index.need | 174 |
| abstract_inverted_index.only | 173 |
| abstract_inverted_index.over | 167 |
| abstract_inverted_index.seek | 74 |
| abstract_inverted_index.that | 201 |
| abstract_inverted_index.then | 185 |
| abstract_inverted_index.this | 31, 71, 131 |
| abstract_inverted_index.with | 208, 219 |
| abstract_inverted_index.(TTA) | 2 |
| abstract_inverted_index.These | 45 |
| abstract_inverted_index.adapt | 15 |
| abstract_inverted_index.broad | 23 |
| abstract_inverted_index.data, | 21, 212 |
| abstract_inverted_index.fewer | 209 |
| abstract_inverted_index.layer | 143 |
| abstract_inverted_index.learn | 101 |
| abstract_inverted_index.model | 8 |
| abstract_inverted_index.noisy | 42 |
| abstract_inverted_index.prior | 86 |
| abstract_inverted_index.small | 176 |
| abstract_inverted_index.speed | 233 |
| abstract_inverted_index.these | 77 |
| abstract_inverted_index.using | 10, 88 |
| abstract_inverted_index.which | 50 |
| abstract_inverted_index.(MGG). | 108 |
| abstract_inverted_index.Unlike | 85 |
| abstract_inverted_index.better | 164 |
| abstract_inverted_index.called | 104 |
| abstract_inverted_index.design | 136 |
| abstract_inverted_index.during | 120 |
| abstract_inverted_index.employ | 95 |
| abstract_inverted_index.faster | 231 |
| abstract_inverted_index.hinder | 51 |
| abstract_inverted_index.issues | 78 |
| abstract_inverted_index.layer. | 147 |
| abstract_inverted_index.memory | 146 |
| abstract_inverted_index.method | 203 |
| abstract_inverted_index.model. | 129 |
| abstract_inverted_index.number | 177 |
| abstract_inverted_index.online | 9, 122 |
| abstract_inverted_index.paper, | 72 |
| abstract_inverted_index.times. | 217 |
| abstract_inverted_index.unseen | 194 |
| abstract_inverted_index.ability | 54, 166 |
| abstract_inverted_index.achieve | 225 |
| abstract_inverted_index.current | 128, 205 |
| abstract_inverted_index.design. | 84 |
| abstract_inverted_index.entropy | 38 |
| abstract_inverted_index.methods | 207 |
| abstract_inverted_index.network | 160 |
| abstract_inverted_index.optimal | 59 |
| abstract_inverted_index.process | 124, 193 |
| abstract_inverted_index.produce | 47 |
| abstract_inverted_index.quickly | 61 |
| abstract_inverted_index.resolve | 76 |
| abstract_inverted_index.results | 197 |
| abstract_inverted_index.samples | 180 |
| abstract_inverted_index.shorter | 215 |
| abstract_inverted_index.signals | 46 |
| abstract_inverted_index.testing | 12 |
| abstract_inverted_index.thereby | 162 |
| abstract_inverted_index.trained | 7, 187 |
| abstract_inverted_index.utilize | 116 |
| abstract_inverted_index.Compared | 218 |
| abstract_inverted_index.Gradient | 106 |
| abstract_inverted_index.However, | 29 |
| abstract_inverted_index.accuracy | 227 |
| abstract_inverted_index.approach | 98 |
| abstract_inverted_index.compress | 155 |
| abstract_inverted_index.converge | 56 |
| abstract_inverted_index.deployed | 191 |
| abstract_inverted_index.designed | 90 |
| abstract_inverted_index.enabling | 163 |
| abstract_inverted_index.exploits | 149 |
| abstract_inverted_index.gradient | 118, 145, 157 |
| abstract_inverted_index.indicate | 200 |
| abstract_inverted_index.learning | 35, 43 |
| abstract_inverted_index.manually | 89 |
| abstract_inverted_index.modeling | 142 |
| abstract_inverted_index.optimize | 126 |
| abstract_inverted_index.previous | 221 |
| abstract_inverted_index.process, | 33 |
| abstract_inverted_index.process. | 69, 171 |
| abstract_inverted_index.samples. | 195 |
| abstract_inverted_index.sequence | 141 |
| abstract_inverted_index.signals. | 44 |
| abstract_inverted_index.solution | 60 |
| abstract_inverted_index.updates, | 210 |
| abstract_inverted_index.Generator | 107 |
| abstract_inverted_index.Promising | 196 |
| abstract_inverted_index.Test-time | 0 |
| abstract_inverted_index.efficient | 140 |
| abstract_inverted_index.encounter | 41 |
| abstract_inverted_index.fine-tune | 5 |
| abstract_inverted_index.introduce | 63 |
| abstract_inverted_index.long-term | 169 |
| abstract_inverted_index.model’s | 53 |
| abstract_inverted_index.optimizer | 83 |
| abstract_inverted_index.potential | 25 |
| abstract_inverted_index.pre-train | 182 |
| abstract_inverted_index.surpasses | 204 |
| abstract_inverted_index.unlabeled | 11, 179 |
| abstract_inverted_index.adaptation | 1, 170, 216, 232 |
| abstract_inverted_index.frequently | 40 |
| abstract_inverted_index.gradients, | 49 |
| abstract_inverted_index.historical | 117, 156 |
| abstract_inverted_index.objectives | 36 |
| abstract_inverted_index.optimizer, | 103 |
| abstract_inverted_index.optimizers | 91 |
| abstract_inverted_index.real-world | 27 |
| abstract_inverted_index.scenarios. | 28 |
| abstract_inverted_index.unreliable | 48 |
| abstract_inverted_index.ImageNet-C. | 235 |
| abstract_inverted_index.application | 24 |
| abstract_inverted_index.effectively | 115 |
| abstract_inverted_index.improvement | 228 |
| abstract_inverted_index.information | 119, 158 |
| abstract_inverted_index.instability | 65 |
| abstract_inverted_index.lightweight | 138 |
| abstract_inverted_index.parameters, | 161 |
| abstract_inverted_index.perspective | 81 |
| abstract_inverted_index.significant | 64 |
| abstract_inverted_index.environments | 18 |
| abstract_inverted_index.memorization | 165 |
| abstract_inverted_index.minimization | 39 |
| abstract_inverted_index.optimization | 32, 68, 123 |
| abstract_inverted_index.unsupervised | 34 |
| abstract_inverted_index.Specifically, | 109 |
| abstract_inverted_index.automatically | 100 |
| abstract_inverted_index.demonstrating | 22 |
| abstract_inverted_index.significantly | 214 |
| abstract_inverted_index.reconstruction | 152 |
| abstract_inverted_index.self-supervised | 151 |
| abstract_inverted_index.state-of-the-art | 206 |
| abstract_inverted_index.out-of-distribution | 20 |
| abstract_inverted_index.learning-to-optimize | 97 |
| abstract_inverted_index.ImageNet-C/R/Sketch/A | 199 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile.value | 0.15254237 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |