SegFace: Face Segmentation of Long-Tail Classes Article Swipe
Kartik Narayan
,
Vibashan VS
,
Vishal M. Patel
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i6.32661
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i6.32661
Face parsing refers to the semantic segmentation of human faces into key facial regions such as eyes, nose, hair, etc. It serves as a prerequisite for various advanced applications, including face editing, face swapping, and facial makeup, which often require segmentation masks for classes like eyeglasses, hats, earrings, and necklaces. These infrequently occurring classes are called long-tail classes, which are overshadowed by more frequently occurring classes known as head classes. Existing methods, primarily CNN-based, tend to be dominated by head classes during training, resulting in suboptimal representation for long-tail classes. Previous works have largely overlooked the problem of poor segmentation performance of long-tail classes. To address this issue, we propose SegFace, a simple and efficient approach that uses a lightweight transformer-based model which utilizes learnable class-specific tokens. The transformer decoder leverages class-specific tokens, allowing each token to focus on its corresponding class, thereby enabling independent modeling of each class. The proposed approach improves the performance of long-tail classes, thereby boosting overall performance. To the best of our knowledge, SegFace is the first work to employ transformer models for face parsing. Moreover, our approach can be adapted for low-compute edge devices, achieving 95.96 FPS. We conduct extensive experiments demonstrating that SegFace significantly outperforms previous state-of-the-art models, achieving a mean F1 score of 88.96 (+2.82) on the CelebAMask-HQ dataset and 93.03 (+0.65) on the LaPa dataset.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i6.32661
- OA Status
- diamond
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409367647
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409367647Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i6.32661Digital Object Identifier
- Title
-
SegFace: Face Segmentation of Long-Tail ClassesWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Kartik Narayan, Vibashan VS, Vishal M. PatelList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i6.32661Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1609/aaai.v39i6.32661Direct OA link when available
- Concepts
-
Face (sociological concept), Segmentation, Artificial intelligence, Computer vision, Computer science, Linguistics, PhilosophyTop 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/W4409367647 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i6.32661 |
| ids.doi | https://doi.org/10.1609/aaai.v39i6.32661 |
| ids.openalex | https://openalex.org/W4409367647 |
| fwci | 0.0 |
| type | article |
| title | SegFace: Face Segmentation of Long-Tail Classes |
| biblio.issue | 6 |
| biblio.volume | 39 |
| biblio.last_page | 6190 |
| biblio.first_page | 6182 |
| topics[0].id | https://openalex.org/T10057 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.33390000462532043 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Face and Expression Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2779304628 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7053081393241882 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q3503480 |
| concepts[0].display_name | Face (sociological concept) |
| concepts[1].id | https://openalex.org/C89600930 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5949693918228149 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[1].display_name | Segmentation |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4810121953487396 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C31972630 |
| concepts[3].level | 1 |
| concepts[3].score | 0.41376304626464844 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[3].display_name | Computer vision |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.40668225288391113 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C41895202 |
| concepts[5].level | 1 |
| concepts[5].score | 0.11229658126831055 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[5].display_name | Linguistics |
| concepts[6].id | https://openalex.org/C138885662 |
| concepts[6].level | 0 |
| concepts[6].score | 0.07693615555763245 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[6].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/face |
| keywords[0].score | 0.7053081393241882 |
| keywords[0].display_name | Face (sociological concept) |
| keywords[1].id | https://openalex.org/keywords/segmentation |
| keywords[1].score | 0.5949693918228149 |
| keywords[1].display_name | Segmentation |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.4810121953487396 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-vision |
| keywords[3].score | 0.41376304626464844 |
| keywords[3].display_name | Computer vision |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.40668225288391113 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/linguistics |
| keywords[5].score | 0.11229658126831055 |
| keywords[5].display_name | Linguistics |
| keywords[6].id | https://openalex.org/keywords/philosophy |
| keywords[6].score | 0.07693615555763245 |
| keywords[6].display_name | Philosophy |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i6.32661 |
| 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 | |
| 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.v39i6.32661 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5112780566 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Kartik Narayan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Kartik Narayan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5004330920 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Vibashan VS |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Vibashan Vs |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5004716468 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5239-692X |
| authorships[2].author.display_name | Vishal M. Patel |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Vishal M. Patel |
| authorships[2].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://doi.org/10.1609/aaai.v39i6.32661 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SegFace: Face Segmentation of Long-Tail Classes |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10057 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.33390000462532043 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Face and Expression Recognition |
| related_works | https://openalex.org/W2772917594, https://openalex.org/W2036807459, https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i6.32661 |
| 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 | |
| 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.v39i6.32661 |
| primary_location.id | doi:10.1609/aaai.v39i6.32661 |
| 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 | |
| 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.v39i6.32661 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 23, 111, 118, 206 |
| abstract_inverted_index.F1 | 208 |
| abstract_inverted_index.It | 20 |
| abstract_inverted_index.To | 104, 162 |
| abstract_inverted_index.We | 193 |
| abstract_inverted_index.as | 15, 22, 67 |
| abstract_inverted_index.be | 76, 184 |
| abstract_inverted_index.by | 61, 78 |
| abstract_inverted_index.in | 84 |
| abstract_inverted_index.is | 169 |
| abstract_inverted_index.of | 7, 97, 101, 146, 155, 165, 210 |
| abstract_inverted_index.on | 138, 213, 220 |
| abstract_inverted_index.to | 3, 75, 136, 173 |
| abstract_inverted_index.we | 108 |
| abstract_inverted_index.The | 127, 149 |
| abstract_inverted_index.and | 34, 48, 113, 217 |
| abstract_inverted_index.are | 54, 59 |
| abstract_inverted_index.can | 183 |
| abstract_inverted_index.for | 25, 42, 87, 177, 186 |
| abstract_inverted_index.its | 139 |
| abstract_inverted_index.key | 11 |
| abstract_inverted_index.our | 166, 181 |
| abstract_inverted_index.the | 4, 95, 153, 163, 170, 214, 221 |
| abstract_inverted_index.FPS. | 192 |
| abstract_inverted_index.Face | 0 |
| abstract_inverted_index.LaPa | 222 |
| abstract_inverted_index.best | 164 |
| abstract_inverted_index.each | 134, 147 |
| abstract_inverted_index.edge | 188 |
| abstract_inverted_index.etc. | 19 |
| abstract_inverted_index.face | 30, 32, 178 |
| abstract_inverted_index.have | 92 |
| abstract_inverted_index.head | 68, 79 |
| abstract_inverted_index.into | 10 |
| abstract_inverted_index.like | 44 |
| abstract_inverted_index.mean | 207 |
| abstract_inverted_index.more | 62 |
| abstract_inverted_index.poor | 98 |
| abstract_inverted_index.such | 14 |
| abstract_inverted_index.tend | 74 |
| abstract_inverted_index.that | 116, 198 |
| abstract_inverted_index.this | 106 |
| abstract_inverted_index.uses | 117 |
| abstract_inverted_index.work | 172 |
| abstract_inverted_index.88.96 | 211 |
| abstract_inverted_index.93.03 | 218 |
| abstract_inverted_index.95.96 | 191 |
| abstract_inverted_index.These | 50 |
| abstract_inverted_index.eyes, | 16 |
| abstract_inverted_index.faces | 9 |
| abstract_inverted_index.first | 171 |
| abstract_inverted_index.focus | 137 |
| abstract_inverted_index.hair, | 18 |
| abstract_inverted_index.hats, | 46 |
| abstract_inverted_index.human | 8 |
| abstract_inverted_index.known | 66 |
| abstract_inverted_index.masks | 41 |
| abstract_inverted_index.model | 121 |
| abstract_inverted_index.nose, | 17 |
| abstract_inverted_index.often | 38 |
| abstract_inverted_index.score | 209 |
| abstract_inverted_index.token | 135 |
| abstract_inverted_index.which | 37, 58, 122 |
| abstract_inverted_index.works | 91 |
| abstract_inverted_index.called | 55 |
| abstract_inverted_index.class, | 141 |
| abstract_inverted_index.class. | 148 |
| abstract_inverted_index.during | 81 |
| abstract_inverted_index.employ | 174 |
| abstract_inverted_index.facial | 12, 35 |
| abstract_inverted_index.issue, | 107 |
| abstract_inverted_index.models | 176 |
| abstract_inverted_index.refers | 2 |
| abstract_inverted_index.serves | 21 |
| abstract_inverted_index.simple | 112 |
| abstract_inverted_index.(+0.65) | 219 |
| abstract_inverted_index.(+2.82) | 212 |
| abstract_inverted_index.SegFace | 168, 199 |
| abstract_inverted_index.adapted | 185 |
| abstract_inverted_index.address | 105 |
| abstract_inverted_index.classes | 43, 53, 65, 80 |
| abstract_inverted_index.conduct | 194 |
| abstract_inverted_index.dataset | 216 |
| abstract_inverted_index.decoder | 129 |
| abstract_inverted_index.largely | 93 |
| abstract_inverted_index.makeup, | 36 |
| abstract_inverted_index.models, | 204 |
| abstract_inverted_index.overall | 160 |
| abstract_inverted_index.parsing | 1 |
| abstract_inverted_index.problem | 96 |
| abstract_inverted_index.propose | 109 |
| abstract_inverted_index.regions | 13 |
| abstract_inverted_index.require | 39 |
| abstract_inverted_index.thereby | 142, 158 |
| abstract_inverted_index.tokens, | 132 |
| abstract_inverted_index.tokens. | 126 |
| abstract_inverted_index.various | 26 |
| abstract_inverted_index.Existing | 70 |
| abstract_inverted_index.Previous | 90 |
| abstract_inverted_index.SegFace, | 110 |
| abstract_inverted_index.advanced | 27 |
| abstract_inverted_index.allowing | 133 |
| abstract_inverted_index.approach | 115, 151, 182 |
| abstract_inverted_index.boosting | 159 |
| abstract_inverted_index.classes, | 57, 157 |
| abstract_inverted_index.classes. | 69, 89, 103 |
| abstract_inverted_index.dataset. | 223 |
| abstract_inverted_index.devices, | 189 |
| abstract_inverted_index.editing, | 31 |
| abstract_inverted_index.enabling | 143 |
| abstract_inverted_index.improves | 152 |
| abstract_inverted_index.methods, | 71 |
| abstract_inverted_index.modeling | 145 |
| abstract_inverted_index.parsing. | 179 |
| abstract_inverted_index.previous | 202 |
| abstract_inverted_index.proposed | 150 |
| abstract_inverted_index.semantic | 5 |
| abstract_inverted_index.utilizes | 123 |
| abstract_inverted_index.Moreover, | 180 |
| abstract_inverted_index.achieving | 190, 205 |
| abstract_inverted_index.dominated | 77 |
| abstract_inverted_index.earrings, | 47 |
| abstract_inverted_index.efficient | 114 |
| abstract_inverted_index.extensive | 195 |
| abstract_inverted_index.including | 29 |
| abstract_inverted_index.learnable | 124 |
| abstract_inverted_index.leverages | 130 |
| abstract_inverted_index.long-tail | 56, 88, 102, 156 |
| abstract_inverted_index.occurring | 52, 64 |
| abstract_inverted_index.primarily | 72 |
| abstract_inverted_index.resulting | 83 |
| abstract_inverted_index.swapping, | 33 |
| abstract_inverted_index.training, | 82 |
| abstract_inverted_index.CNN-based, | 73 |
| abstract_inverted_index.frequently | 63 |
| abstract_inverted_index.knowledge, | 167 |
| abstract_inverted_index.necklaces. | 49 |
| abstract_inverted_index.overlooked | 94 |
| abstract_inverted_index.suboptimal | 85 |
| abstract_inverted_index.experiments | 196 |
| abstract_inverted_index.eyeglasses, | 45 |
| abstract_inverted_index.independent | 144 |
| abstract_inverted_index.lightweight | 119 |
| abstract_inverted_index.low-compute | 187 |
| abstract_inverted_index.outperforms | 201 |
| abstract_inverted_index.performance | 100, 154 |
| abstract_inverted_index.transformer | 128, 175 |
| abstract_inverted_index.infrequently | 51 |
| abstract_inverted_index.overshadowed | 60 |
| abstract_inverted_index.performance. | 161 |
| abstract_inverted_index.prerequisite | 24 |
| abstract_inverted_index.segmentation | 6, 40, 99 |
| abstract_inverted_index.CelebAMask-HQ | 215 |
| abstract_inverted_index.applications, | 28 |
| abstract_inverted_index.corresponding | 140 |
| abstract_inverted_index.demonstrating | 197 |
| abstract_inverted_index.significantly | 200 |
| abstract_inverted_index.class-specific | 125, 131 |
| abstract_inverted_index.representation | 86 |
| abstract_inverted_index.state-of-the-art | 203 |
| abstract_inverted_index.transformer-based | 120 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.36156764 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |