Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling Article Swipe
David Williams
,
Matthew Gadd
,
Paul Newman
,
Daniele De Martini
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.17622
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.17622
This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach, which is robust to augmentation hyper-parameters and simpler than previous techniques. For neural networks used in safety-critical applications, bias in the training data can lead to errors; therefore it is crucial to understand a network's limitations at run time and act accordingly. To this end, we test our proposed method on a number of test domains including the SAX Segmentation benchmark, which includes labelled test data from dense urban, rural and off-road driving domains. The proposed method consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2402.17622
- https://arxiv.org/pdf/2402.17622
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392271363
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392271363Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2402.17622Digital Object Identifier
- Title
-
Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image ModelingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-02-27Full publication date if available
- Authors
-
David Williams, Matthew Gadd, Paul Newman, Daniele De MartiniList of authors in order
- Landing page
-
https://arxiv.org/abs/2402.17622Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2402.17622Direct 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/2402.17622Direct OA link when available
- Concepts
-
Estimation, Computer science, Image (mathematics), Artificial intelligence, Econometrics, Computer vision, Machine learning, Mathematics, Economics, ManagementTop 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/W4392271363 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2402.17622 |
| ids.doi | https://doi.org/10.48550/arxiv.2402.17622 |
| ids.openalex | https://openalex.org/W4392271363 |
| fwci | |
| type | preprint |
| title | Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10876 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9796000123023987 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2207 |
| topics[0].subfield.display_name | Control and Systems Engineering |
| topics[0].display_name | Fault Detection and Control Systems |
| topics[1].id | https://openalex.org/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.934499979019165 |
| 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 | Anomaly Detection Techniques and Applications |
| topics[2].id | https://openalex.org/T12072 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9133999943733215 |
| 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 Algorithms |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C96250715 |
| concepts[0].level | 2 |
| concepts[0].score | 0.5531163811683655 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q965330 |
| concepts[0].display_name | Estimation |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5233099460601807 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C115961682 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5206450819969177 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[2].display_name | Image (mathematics) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5078080296516418 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C149782125 |
| concepts[4].level | 1 |
| concepts[4].score | 0.40390318632125854 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q160039 |
| concepts[4].display_name | Econometrics |
| concepts[5].id | https://openalex.org/C31972630 |
| concepts[5].level | 1 |
| concepts[5].score | 0.40019112825393677 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[5].display_name | Computer vision |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.32305529713630676 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.22080695629119873 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C162324750 |
| concepts[8].level | 0 |
| concepts[8].score | 0.17679202556610107 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[8].display_name | Economics |
| concepts[9].id | https://openalex.org/C187736073 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[9].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/estimation |
| keywords[0].score | 0.5531163811683655 |
| keywords[0].display_name | Estimation |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5233099460601807 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/image |
| keywords[2].score | 0.5206450819969177 |
| keywords[2].display_name | Image (mathematics) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5078080296516418 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/econometrics |
| keywords[4].score | 0.40390318632125854 |
| keywords[4].display_name | Econometrics |
| keywords[5].id | https://openalex.org/keywords/computer-vision |
| keywords[5].score | 0.40019112825393677 |
| keywords[5].display_name | Computer vision |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.32305529713630676 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.22080695629119873 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/economics |
| keywords[8].score | 0.17679202556610107 |
| keywords[8].display_name | Economics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2402.17622 |
| 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/2402.17622 |
| 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/2402.17622 |
| locations[1].id | doi:10.48550/arxiv.2402.17622 |
| 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.2402.17622 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5068999650 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0531-9785 |
| authorships[0].author.display_name | David Williams |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Williams, David S. W. |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5040498612 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9447-8619 |
| authorships[1].author.display_name | Matthew Gadd |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gadd, Matthew |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5055299977 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6562-8454 |
| authorships[2].author.display_name | Paul Newman |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Newman, Paul |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5074335131 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6121-5839 |
| authorships[3].author.display_name | Daniele De Martini |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | De Martini, Daniele |
| authorships[3].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/2402.17622 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-03-05T00:00:00 |
| display_name | Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10876 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9796000123023987 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2207 |
| primary_topic.subfield.display_name | Control and Systems Engineering |
| primary_topic.display_name | Fault Detection and Control Systems |
| related_works | https://openalex.org/W2576994247, https://openalex.org/W2608353378, https://openalex.org/W4249206767, https://openalex.org/W2563559453, https://openalex.org/W2382330008, https://openalex.org/W1519970947, https://openalex.org/W4243860260, https://openalex.org/W2961085424, https://openalex.org/W4383503847, https://openalex.org/W2342695897 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2402.17622 |
| 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/2402.17622 |
| 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/2402.17622 |
| primary_location.id | pmh:oai:arXiv.org:2402.17622 |
| 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/2402.17622 |
| 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/2402.17622 |
| publication_date | 2024-02-27 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 3, 13, 28, 67, 85 |
| abstract_inverted_index.To | 76 |
| abstract_inverted_index.We | 17 |
| abstract_inverted_index.at | 70 |
| abstract_inverted_index.in | 12, 49, 53 |
| abstract_inverted_index.is | 35, 63 |
| abstract_inverted_index.it | 62 |
| abstract_inverted_index.of | 87 |
| abstract_inverted_index.on | 84, 119 |
| abstract_inverted_index.to | 37, 59, 65 |
| abstract_inverted_index.we | 79 |
| abstract_inverted_index.For | 45 |
| abstract_inverted_index.SAX | 92 |
| abstract_inverted_index.The | 108 |
| abstract_inverted_index.act | 74 |
| abstract_inverted_index.and | 24, 40, 73, 104, 115 |
| abstract_inverted_index.can | 57 |
| abstract_inverted_index.our | 81 |
| abstract_inverted_index.run | 71 |
| abstract_inverted_index.the | 54, 91 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.bias | 52 |
| abstract_inverted_index.data | 56, 99 |
| abstract_inverted_index.end, | 78 |
| abstract_inverted_index.from | 21, 100 |
| abstract_inverted_index.lead | 58 |
| abstract_inverted_index.test | 80, 88, 98 |
| abstract_inverted_index.than | 42 |
| abstract_inverted_index.that | 7 |
| abstract_inverted_index.this | 77, 120 |
| abstract_inverted_index.time | 72 |
| abstract_inverted_index.used | 48 |
| abstract_inverted_index.work | 1 |
| abstract_inverted_index.(MIM) | 32 |
| abstract_inverted_index.(OoD) | 117 |
| abstract_inverted_index.Image | 30 |
| abstract_inverted_index.dense | 101 |
| abstract_inverted_index.pass. | 16 |
| abstract_inverted_index.rural | 103 |
| abstract_inverted_index.which | 34, 95 |
| abstract_inverted_index.Masked | 29 |
| abstract_inverted_index.method | 83, 110 |
| abstract_inverted_index.models | 23 |
| abstract_inverted_index.neural | 46 |
| abstract_inverted_index.number | 86 |
| abstract_inverted_index.robust | 36 |
| abstract_inverted_index.single | 14 |
| abstract_inverted_index.urban, | 102 |
| abstract_inverted_index.crucial | 64 |
| abstract_inverted_index.domains | 89 |
| abstract_inverted_index.driving | 106 |
| abstract_inverted_index.errors; | 60 |
| abstract_inverted_index.exploit | 18 |
| abstract_inverted_index.forward | 15 |
| abstract_inverted_index.general | 19 |
| abstract_inverted_index.network | 6 |
| abstract_inverted_index.simpler | 41 |
| abstract_inverted_index.through | 27 |
| abstract_inverted_index.Modeling | 31 |
| abstract_inverted_index.datasets | 26 |
| abstract_inverted_index.domains. | 107 |
| abstract_inverted_index.includes | 96 |
| abstract_inverted_index.labelled | 97 |
| abstract_inverted_index.networks | 47 |
| abstract_inverted_index.off-road | 105 |
| abstract_inverted_index.previous | 43 |
| abstract_inverted_index.produces | 8 |
| abstract_inverted_index.proposed | 82, 109 |
| abstract_inverted_index.proposes | 2 |
| abstract_inverted_index.semantic | 4 |
| abstract_inverted_index.training | 55 |
| abstract_inverted_index.approach, | 33 |
| abstract_inverted_index.difficult | 121 |
| abstract_inverted_index.estimates | 11 |
| abstract_inverted_index.including | 90 |
| abstract_inverted_index.network's | 68 |
| abstract_inverted_index.therefore | 61 |
| abstract_inverted_index.benchmark, | 94 |
| abstract_inverted_index.benchmark. | 122 |
| abstract_inverted_index.estimation | 114 |
| abstract_inverted_index.foundation | 22 |
| abstract_inverted_index.techniques | 118 |
| abstract_inverted_index.understand | 66 |
| abstract_inverted_index.unlabelled | 25 |
| abstract_inverted_index.limitations | 69 |
| abstract_inverted_index.outperforms | 112 |
| abstract_inverted_index.techniques. | 44 |
| abstract_inverted_index.uncertainty | 10, 113 |
| abstract_inverted_index.Segmentation | 93 |
| abstract_inverted_index.accordingly. | 75 |
| abstract_inverted_index.augmentation | 38 |
| abstract_inverted_index.consistently | 111 |
| abstract_inverted_index.high-quality | 9 |
| abstract_inverted_index.segmentation | 5 |
| abstract_inverted_index.applications, | 51 |
| abstract_inverted_index.representations | 20 |
| abstract_inverted_index.safety-critical | 50 |
| abstract_inverted_index.hyper-parameters | 39 |
| abstract_inverted_index.Out-of-Distribution | 116 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |