Out-of-Distribution Detection with Overlap Index Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.06168
Out-of-distribution (OOD) detection is crucial for the deployment of machine learning models in the open world. While existing OOD detectors are effective in identifying OOD samples that deviate significantly from in-distribution (ID) data, they often come with trade-offs. For instance, deep OOD detectors usually suffer from high computational costs, require tuning hyperparameters, and have limited interpretability, whereas traditional OOD detectors may have a low accuracy on large high-dimensional datasets. To address these limitations, we propose a novel effective OOD detection approach that employs an overlap index (OI)-based confidence score function to evaluate the likelihood of a given input belonging to the same distribution as the available ID samples. The proposed OI-based confidence score function is non-parametric, lightweight, and easy to interpret, hence providing strong flexibility and generality. Extensive empirical evaluations indicate that our OI-based OOD detector is competitive with state-of-the-art OOD detectors in terms of detection accuracy on a wide range of datasets while requiring less computation and memory costs. Lastly, we show that the proposed OI-based confidence score function inherits nice properties from OI (e.g., insensitivity to small distributional variations and robustness against Huber $ε$-contamination) and is a versatile tool for estimating OI and model accuracy in specific contexts.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2412.06168
- https://arxiv.org/pdf/2412.06168
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4405253966
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4405253966Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2412.06168Digital Object Identifier
- Title
-
Out-of-Distribution Detection with Overlap IndexWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-12-09Full publication date if available
- Authors
-
Hao Fu, P. Krishnamurthy, Siddharth Garg, Farshad KhorramiList of authors in order
- Landing page
-
https://arxiv.org/abs/2412.06168Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2412.06168Direct 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/2412.06168Direct OA link when available
- Concepts
-
Index (typography), Distribution (mathematics), Statistics, Geography, Mathematics, Computer science, World Wide Web, Mathematical analysisTop 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/W4405253966 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2412.06168 |
| ids.doi | https://doi.org/10.48550/arxiv.2412.06168 |
| ids.openalex | https://openalex.org/W4405253966 |
| fwci | |
| type | preprint |
| title | Out-of-Distribution Detection with Overlap Index |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9639000296592712 |
| 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 | Anomaly Detection Techniques and Applications |
| topics[1].id | https://openalex.org/T12879 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9370999932289124 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1705 |
| topics[1].subfield.display_name | Computer Networks and Communications |
| topics[1].display_name | Distributed Sensor Networks and Detection Algorithms |
| topics[2].id | https://openalex.org/T10876 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9232000112533569 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2207 |
| topics[2].subfield.display_name | Control and Systems Engineering |
| topics[2].display_name | Fault Detection and Control Systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2777382242 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6103588938713074 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6017816 |
| concepts[0].display_name | Index (typography) |
| concepts[1].id | https://openalex.org/C110121322 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5008184909820557 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q865811 |
| concepts[1].display_name | Distribution (mathematics) |
| concepts[2].id | https://openalex.org/C105795698 |
| concepts[2].level | 1 |
| concepts[2].score | 0.41668444871902466 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[2].display_name | Statistics |
| concepts[3].id | https://openalex.org/C205649164 |
| concepts[3].level | 0 |
| concepts[3].score | 0.37386268377304077 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[3].display_name | Geography |
| concepts[4].id | https://openalex.org/C33923547 |
| concepts[4].level | 0 |
| concepts[4].score | 0.3244730234146118 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[4].display_name | Mathematics |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.27694979310035706 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C136764020 |
| concepts[6].level | 1 |
| concepts[6].score | 0.08209171891212463 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q466 |
| concepts[6].display_name | World Wide Web |
| concepts[7].id | https://openalex.org/C134306372 |
| concepts[7].level | 1 |
| concepts[7].score | 0.05856236815452576 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[7].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/index |
| keywords[0].score | 0.6103588938713074 |
| keywords[0].display_name | Index (typography) |
| keywords[1].id | https://openalex.org/keywords/distribution |
| keywords[1].score | 0.5008184909820557 |
| keywords[1].display_name | Distribution (mathematics) |
| keywords[2].id | https://openalex.org/keywords/statistics |
| keywords[2].score | 0.41668444871902466 |
| keywords[2].display_name | Statistics |
| keywords[3].id | https://openalex.org/keywords/geography |
| keywords[3].score | 0.37386268377304077 |
| keywords[3].display_name | Geography |
| keywords[4].id | https://openalex.org/keywords/mathematics |
| keywords[4].score | 0.3244730234146118 |
| keywords[4].display_name | Mathematics |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.27694979310035706 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/world-wide-web |
| keywords[6].score | 0.08209171891212463 |
| keywords[6].display_name | World Wide Web |
| keywords[7].id | https://openalex.org/keywords/mathematical-analysis |
| keywords[7].score | 0.05856236815452576 |
| keywords[7].display_name | Mathematical analysis |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2412.06168 |
| 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/2412.06168 |
| 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/2412.06168 |
| locations[1].id | doi:10.48550/arxiv.2412.06168 |
| 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.2412.06168 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101719489 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9300-9383 |
| authorships[0].author.display_name | Hao Fu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Fu, Hao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5054769060 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8264-7972 |
| authorships[1].author.display_name | P. Krishnamurthy |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Krishnamurthy, Prashanth |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5010950688 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6158-9512 |
| authorships[2].author.display_name | Siddharth Garg |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Garg, Siddharth |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5082413942 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8418-004X |
| authorships[3].author.display_name | Farshad Khorrami |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Khorrami, Farshad |
| 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/2412.06168 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Out-of-Distribution Detection with Overlap Index |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9639000296592712 |
| 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 | Anomaly Detection Techniques and Applications |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W1979597421, https://openalex.org/W2007980826, https://openalex.org/W2061531152, https://openalex.org/W3002753104, https://openalex.org/W2077600819, https://openalex.org/W2142036596, https://openalex.org/W2072657027, https://openalex.org/W2962838298 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2412.06168 |
| 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/2412.06168 |
| 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/2412.06168 |
| primary_location.id | pmh:oai:arXiv.org:2412.06168 |
| 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/2412.06168 |
| 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/2412.06168 |
| publication_date | 2024-12-09 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 62, 75, 95, 148, 188 |
| abstract_inverted_index.ID | 106 |
| abstract_inverted_index.OI | 174, 193 |
| abstract_inverted_index.To | 69 |
| abstract_inverted_index.an | 83 |
| abstract_inverted_index.as | 103 |
| abstract_inverted_index.in | 12, 22, 142, 197 |
| abstract_inverted_index.is | 3, 114, 136, 187 |
| abstract_inverted_index.of | 8, 94, 144, 151 |
| abstract_inverted_index.on | 65, 147 |
| abstract_inverted_index.to | 90, 99, 119, 177 |
| abstract_inverted_index.we | 73, 161 |
| abstract_inverted_index.For | 38 |
| abstract_inverted_index.OOD | 18, 24, 41, 58, 78, 134, 140 |
| abstract_inverted_index.The | 108 |
| abstract_inverted_index.and | 52, 117, 125, 157, 181, 186, 194 |
| abstract_inverted_index.are | 20 |
| abstract_inverted_index.for | 5, 191 |
| abstract_inverted_index.low | 63 |
| abstract_inverted_index.may | 60 |
| abstract_inverted_index.our | 132 |
| abstract_inverted_index.the | 6, 13, 92, 100, 104, 164 |
| abstract_inverted_index.(ID) | 31 |
| abstract_inverted_index.come | 35 |
| abstract_inverted_index.deep | 40 |
| abstract_inverted_index.easy | 118 |
| abstract_inverted_index.from | 29, 45, 173 |
| abstract_inverted_index.have | 53, 61 |
| abstract_inverted_index.high | 46 |
| abstract_inverted_index.less | 155 |
| abstract_inverted_index.nice | 171 |
| abstract_inverted_index.open | 14 |
| abstract_inverted_index.same | 101 |
| abstract_inverted_index.show | 162 |
| abstract_inverted_index.that | 26, 81, 131, 163 |
| abstract_inverted_index.they | 33 |
| abstract_inverted_index.tool | 190 |
| abstract_inverted_index.wide | 149 |
| abstract_inverted_index.with | 36, 138 |
| abstract_inverted_index.(OOD) | 1 |
| abstract_inverted_index.Huber | 184 |
| abstract_inverted_index.While | 16 |
| abstract_inverted_index.data, | 32 |
| abstract_inverted_index.given | 96 |
| abstract_inverted_index.hence | 121 |
| abstract_inverted_index.index | 85 |
| abstract_inverted_index.input | 97 |
| abstract_inverted_index.large | 66 |
| abstract_inverted_index.model | 195 |
| abstract_inverted_index.novel | 76 |
| abstract_inverted_index.often | 34 |
| abstract_inverted_index.range | 150 |
| abstract_inverted_index.score | 88, 112, 168 |
| abstract_inverted_index.small | 178 |
| abstract_inverted_index.terms | 143 |
| abstract_inverted_index.these | 71 |
| abstract_inverted_index.while | 153 |
| abstract_inverted_index.(e.g., | 175 |
| abstract_inverted_index.costs, | 48 |
| abstract_inverted_index.costs. | 159 |
| abstract_inverted_index.memory | 158 |
| abstract_inverted_index.models | 11 |
| abstract_inverted_index.strong | 123 |
| abstract_inverted_index.suffer | 44 |
| abstract_inverted_index.tuning | 50 |
| abstract_inverted_index.world. | 15 |
| abstract_inverted_index.Lastly, | 160 |
| abstract_inverted_index.address | 70 |
| abstract_inverted_index.against | 183 |
| abstract_inverted_index.crucial | 4 |
| abstract_inverted_index.deviate | 27 |
| abstract_inverted_index.employs | 82 |
| abstract_inverted_index.limited | 54 |
| abstract_inverted_index.machine | 9 |
| abstract_inverted_index.overlap | 84 |
| abstract_inverted_index.propose | 74 |
| abstract_inverted_index.require | 49 |
| abstract_inverted_index.samples | 25 |
| abstract_inverted_index.usually | 43 |
| abstract_inverted_index.whereas | 56 |
| abstract_inverted_index.OI-based | 110, 133, 166 |
| abstract_inverted_index.accuracy | 64, 146, 196 |
| abstract_inverted_index.approach | 80 |
| abstract_inverted_index.datasets | 152 |
| abstract_inverted_index.detector | 135 |
| abstract_inverted_index.evaluate | 91 |
| abstract_inverted_index.existing | 17 |
| abstract_inverted_index.function | 89, 113, 169 |
| abstract_inverted_index.indicate | 130 |
| abstract_inverted_index.inherits | 170 |
| abstract_inverted_index.learning | 10 |
| abstract_inverted_index.proposed | 109, 165 |
| abstract_inverted_index.samples. | 107 |
| abstract_inverted_index.specific | 198 |
| abstract_inverted_index.Extensive | 127 |
| abstract_inverted_index.available | 105 |
| abstract_inverted_index.belonging | 98 |
| abstract_inverted_index.contexts. | 199 |
| abstract_inverted_index.datasets. | 68 |
| abstract_inverted_index.detection | 2, 79, 145 |
| abstract_inverted_index.detectors | 19, 42, 59, 141 |
| abstract_inverted_index.effective | 21, 77 |
| abstract_inverted_index.empirical | 128 |
| abstract_inverted_index.instance, | 39 |
| abstract_inverted_index.providing | 122 |
| abstract_inverted_index.requiring | 154 |
| abstract_inverted_index.versatile | 189 |
| abstract_inverted_index.(OI)-based | 86 |
| abstract_inverted_index.confidence | 87, 111, 167 |
| abstract_inverted_index.deployment | 7 |
| abstract_inverted_index.estimating | 192 |
| abstract_inverted_index.interpret, | 120 |
| abstract_inverted_index.likelihood | 93 |
| abstract_inverted_index.properties | 172 |
| abstract_inverted_index.robustness | 182 |
| abstract_inverted_index.variations | 180 |
| abstract_inverted_index.competitive | 137 |
| abstract_inverted_index.computation | 156 |
| abstract_inverted_index.evaluations | 129 |
| abstract_inverted_index.flexibility | 124 |
| abstract_inverted_index.generality. | 126 |
| abstract_inverted_index.identifying | 23 |
| abstract_inverted_index.trade-offs. | 37 |
| abstract_inverted_index.traditional | 57 |
| abstract_inverted_index.distribution | 102 |
| abstract_inverted_index.lightweight, | 116 |
| abstract_inverted_index.limitations, | 72 |
| abstract_inverted_index.computational | 47 |
| abstract_inverted_index.insensitivity | 176 |
| abstract_inverted_index.significantly | 28 |
| abstract_inverted_index.distributional | 179 |
| abstract_inverted_index.in-distribution | 30 |
| abstract_inverted_index.non-parametric, | 115 |
| abstract_inverted_index.high-dimensional | 67 |
| abstract_inverted_index.hyperparameters, | 51 |
| abstract_inverted_index.state-of-the-art | 139 |
| abstract_inverted_index.interpretability, | 55 |
| abstract_inverted_index.$ε$-contamination) | 185 |
| abstract_inverted_index.Out-of-distribution | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |