Learning to Transform for Generalizable Instance-wise Invariance Article Swipe
Utkarsh Singhal
,
Carlos Esteves
,
Ameesh Makadia
,
Stella X. Yu
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.16672
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.16672
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance. Ideally, the appropriate invariance would be learned from data and inferred at test-time. We treat invariance as a prediction problem. Given any image, we use a normalizing flow to predict a distribution over transformations and average the predictions over them. Since this distribution only depends on the instance, we can align instances before classifying them and generalize invariance across classes. The same distribution can also be used to adapt to out-of-distribution poses. This normalizing flow is trained end-to-end and can learn a much larger range of transformations than Augerino and InstaAug. When used as data augmentation, our method shows accuracy and robustness gains on CIFAR 10, CIFAR10-LT, and TinyImageNet.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2309.16672
- https://arxiv.org/pdf/2309.16672
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387226759
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387226759Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2309.16672Digital Object Identifier
- Title
-
Learning to Transform for Generalizable Instance-wise InvarianceWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-09-28Full publication date if available
- Authors
-
Utkarsh Singhal, Carlos Esteves, Ameesh Makadia, Stella X. YuList of authors in order
- Landing page
-
https://arxiv.org/abs/2309.16672Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2309.16672Direct 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/2309.16672Direct OA link when available
- Concepts
-
Robustness (evolution), A priori and a posteriori, Computer science, Artificial intelligence, Range (aeronautics), Pattern recognition (psychology), Algorithm, Mathematics, Machine learning, Gene, Philosophy, Composite material, Chemistry, Materials science, Epistemology, BiochemistryTop 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/W4387226759 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2309.16672 |
| ids.doi | https://doi.org/10.48550/arxiv.2309.16672 |
| ids.openalex | https://openalex.org/W4387226759 |
| fwci | |
| type | preprint |
| title | Learning to Transform for Generalizable Instance-wise Invariance |
| 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 | 0.9968000054359436 |
| 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/T11714 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9926000237464905 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Multimodal Machine Learning Applications |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9894000291824341 |
| 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 | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63479239 |
| concepts[0].level | 3 |
| concepts[0].score | 0.639171838760376 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[0].display_name | Robustness (evolution) |
| concepts[1].id | https://openalex.org/C75553542 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6360546946525574 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q178161 |
| concepts[1].display_name | A priori and a posteriori |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6167807579040527 |
| 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 | 0.5887200832366943 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C204323151 |
| concepts[4].level | 2 |
| concepts[4].score | 0.45775991678237915 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q905424 |
| concepts[4].display_name | Range (aeronautics) |
| concepts[5].id | https://openalex.org/C153180895 |
| concepts[5].level | 2 |
| concepts[5].score | 0.41327595710754395 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[5].display_name | Pattern recognition (psychology) |
| concepts[6].id | https://openalex.org/C11413529 |
| concepts[6].level | 1 |
| concepts[6].score | 0.40437814593315125 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[6].display_name | Algorithm |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.35165369510650635 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33311817049980164 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C104317684 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[9].display_name | Gene |
| concepts[10].id | https://openalex.org/C138885662 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[10].display_name | Philosophy |
| concepts[11].id | https://openalex.org/C159985019 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[11].display_name | Composite material |
| concepts[12].id | https://openalex.org/C185592680 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[12].display_name | Chemistry |
| concepts[13].id | https://openalex.org/C192562407 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[13].display_name | Materials science |
| concepts[14].id | https://openalex.org/C111472728 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[14].display_name | Epistemology |
| concepts[15].id | https://openalex.org/C55493867 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[15].display_name | Biochemistry |
| keywords[0].id | https://openalex.org/keywords/robustness |
| keywords[0].score | 0.639171838760376 |
| keywords[0].display_name | Robustness (evolution) |
| keywords[1].id | https://openalex.org/keywords/a-priori-and-a-posteriori |
| keywords[1].score | 0.6360546946525574 |
| keywords[1].display_name | A priori and a posteriori |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6167807579040527 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5887200832366943 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/range |
| keywords[4].score | 0.45775991678237915 |
| keywords[4].display_name | Range (aeronautics) |
| keywords[5].id | https://openalex.org/keywords/pattern-recognition |
| keywords[5].score | 0.41327595710754395 |
| keywords[5].display_name | Pattern recognition (psychology) |
| keywords[6].id | https://openalex.org/keywords/algorithm |
| keywords[6].score | 0.40437814593315125 |
| keywords[6].display_name | Algorithm |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.35165369510650635 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.33311817049980164 |
| keywords[8].display_name | Machine learning |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2309.16672 |
| 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 | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2309.16672 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2309.16672 |
| locations[1].id | doi:10.48550/arxiv.2309.16672 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2309.16672 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5065706282 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Utkarsh Singhal |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Singhal, Utkarsh |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5030999390 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9413-1201 |
| authorships[1].author.display_name | Carlos Esteves |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Esteves, Carlos |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5087850633 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Ameesh Makadia |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Makadia, Ameesh |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5042014034 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3507-5761 |
| authorships[3].author.display_name | Stella X. Yu |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Yu, Stella X. |
| 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/2309.16672 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning to Transform for Generalizable Instance-wise Invariance |
| 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 | 0.9968000054359436 |
| 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/W4388311650, https://openalex.org/W5922282, https://openalex.org/W1974056099, https://openalex.org/W4245343541, https://openalex.org/W2386077341, https://openalex.org/W563589758, https://openalex.org/W62490179, https://openalex.org/W2954004777, https://openalex.org/W2949638731, https://openalex.org/W2951102138 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2309.16672 |
| 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 | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2309.16672 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| 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/2309.16672 |
| primary_location.id | pmh:oai:arXiv.org:2309.16672 |
| 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 | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2309.16672 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2309.16672 |
| publication_date | 2023-09-28 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 47, 71, 79, 84, 135 |
| abstract_inverted_index.We | 67 |
| abstract_inverted_index.as | 70, 147 |
| abstract_inverted_index.at | 65 |
| abstract_inverted_index.be | 59, 119 |
| abstract_inverted_index.in | 16 |
| abstract_inverted_index.is | 21, 45, 129 |
| abstract_inverted_index.of | 139 |
| abstract_inverted_index.on | 51, 99, 157 |
| abstract_inverted_index.or | 26, 35 |
| abstract_inverted_index.to | 6, 12, 82, 121, 123 |
| abstract_inverted_index.we | 77, 102 |
| abstract_inverted_index.10, | 159 |
| abstract_inverted_index.The | 114 |
| abstract_inverted_index.and | 41, 49, 63, 88, 109, 132, 143, 154, 161 |
| abstract_inverted_index.any | 75 |
| abstract_inverted_index.are | 10 |
| abstract_inverted_index.can | 39, 103, 117, 133 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.our | 150 |
| abstract_inverted_index.the | 30, 42, 52, 55, 90, 100 |
| abstract_inverted_index.too | 33, 36 |
| abstract_inverted_index.use | 78 |
| abstract_inverted_index.This | 126 |
| abstract_inverted_index.When | 145 |
| abstract_inverted_index.also | 118 |
| abstract_inverted_index.data | 24, 62, 148 |
| abstract_inverted_index.done | 22 |
| abstract_inverted_index.flow | 81, 128 |
| abstract_inverted_index.from | 61 |
| abstract_inverted_index.into | 29 |
| abstract_inverted_index.long | 4 |
| abstract_inverted_index.much | 34, 136 |
| abstract_inverted_index.only | 97 |
| abstract_inverted_index.over | 86, 92 |
| abstract_inverted_index.same | 115 |
| abstract_inverted_index.than | 141 |
| abstract_inverted_index.that | 9 |
| abstract_inverted_index.them | 108 |
| abstract_inverted_index.this | 20, 95 |
| abstract_inverted_index.used | 120, 146 |
| abstract_inverted_index.CIFAR | 158 |
| abstract_inverted_index.Given | 74 |
| abstract_inverted_index.Since | 94 |
| abstract_inverted_index.adapt | 122 |
| abstract_inverted_index.aimed | 5 |
| abstract_inverted_index.align | 104 |
| abstract_inverted_index.build | 7 |
| abstract_inverted_index.data. | 18 |
| abstract_inverted_index.found | 15 |
| abstract_inverted_index.gains | 156 |
| abstract_inverted_index.hurt, | 40 |
| abstract_inverted_index.learn | 134 |
| abstract_inverted_index.range | 138 |
| abstract_inverted_index.shows | 152 |
| abstract_inverted_index.them. | 93 |
| abstract_inverted_index.treat | 68 |
| abstract_inverted_index.using | 23 |
| abstract_inverted_index.would | 58 |
| abstract_inverted_index.across | 112 |
| abstract_inverted_index.amount | 44 |
| abstract_inverted_index.before | 106 |
| abstract_inverted_index.image, | 76 |
| abstract_inverted_index.larger | 137 |
| abstract_inverted_index.little | 37 |
| abstract_inverted_index.method | 151 |
| abstract_inverted_index.poses. | 125 |
| abstract_inverted_index.priori | 48 |
| abstract_inverted_index.robust | 11 |
| abstract_inverted_index.vision | 1 |
| abstract_inverted_index.average | 89 |
| abstract_inverted_index.correct | 43 |
| abstract_inverted_index.depends | 98 |
| abstract_inverted_index.learned | 60 |
| abstract_inverted_index.natural | 17 |
| abstract_inverted_index.predict | 83 |
| abstract_inverted_index.spatial | 13 |
| abstract_inverted_index.systems | 8 |
| abstract_inverted_index.trained | 130 |
| abstract_inverted_index.unknown | 46 |
| abstract_inverted_index.Augerino | 142 |
| abstract_inverted_index.Computer | 0 |
| abstract_inverted_index.However, | 32 |
| abstract_inverted_index.Ideally, | 54 |
| abstract_inverted_index.accuracy | 153 |
| abstract_inverted_index.classes. | 113 |
| abstract_inverted_index.inferred | 64 |
| abstract_inverted_index.problem. | 73 |
| abstract_inverted_index.research | 2 |
| abstract_inverted_index.InstaAug. | 144 |
| abstract_inverted_index.dependent | 50 |
| abstract_inverted_index.instance, | 101 |
| abstract_inverted_index.instance. | 53 |
| abstract_inverted_index.instances | 105 |
| abstract_inverted_index.end-to-end | 131 |
| abstract_inverted_index.generalize | 110 |
| abstract_inverted_index.invariance | 38, 57, 69, 111 |
| abstract_inverted_index.prediction | 72 |
| abstract_inverted_index.robustness | 155 |
| abstract_inverted_index.test-time. | 66 |
| abstract_inverted_index.CIFAR10-LT, | 160 |
| abstract_inverted_index.appropriate | 56 |
| abstract_inverted_index.classifying | 107 |
| abstract_inverted_index.hard-coding | 27 |
| abstract_inverted_index.invariances | 28 |
| abstract_inverted_index.normalizing | 80, 127 |
| abstract_inverted_index.predictions | 91 |
| abstract_inverted_index.augmentation | 25 |
| abstract_inverted_index.distribution | 85, 96, 116 |
| abstract_inverted_index.TinyImageNet. | 162 |
| abstract_inverted_index.architecture. | 31 |
| abstract_inverted_index.augmentation, | 149 |
| abstract_inverted_index.Traditionally, | 19 |
| abstract_inverted_index.transformations | 14, 87, 140 |
| abstract_inverted_index.out-of-distribution | 124 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |