Symmetry-Aware Superpixel-Enhanced Few-Shot Semantic Segmentation Article Swipe
Lan Guo
,
Xingran Li
,
Jinqiang Wang
,
Yuqi Tong
,
Jie Xiao
,
Rui Zhou
,
Ling-Huey Li
,
Qingguo Zhou
,
Kuan‐Ching Li
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/sym17101726
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.3390/sym17101726
Few-Shot Semantic Segmentation (FSS) faces significant challenges in modeling complex backgrounds and maintaining prediction consistency due to limited training samples. Existing methods oversimplify backgrounds as single negative classes and rely solely on pixel-level alignments. To address these issues, we propose a symmetry-aware superpixel-enhanced FSS framework with a symmetric dual-branch architecture that explicitly models the superpixel region-graph in both the support and query branches. First, top–down cross-layer fusion injects low-level edge and texture cues into high-level semantics to build a more complete representation of complex backgrounds, improving foreground–background separability and boundary quality. Second, images are partitioned into superpixels and aggregated into “superpixel tokens” to construct a Region Adjacency Graph (RAG). Support-set prototypes are used to initialize query-pixel predictions, which are then projected into the superpixel space for cross-image prototype alignment with support superpixels. We further perform message passing/energy minimization on the RAG to enhance intra-region consistency and boundary adherence, and finally back-project the predictions to the pixel space. Lastly, by aggregating homogeneous semantic information, we construct robust foreground and background prototype representations, enhancing the model’s ability to perceive both seen and novel targets. Extensive experiments on the PASCAL-5i and COCO-20i benchmarks demonstrate that our proposed model achieves superior segmentation performance over the baseline and remains competitive with existing FSS methods.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.3390/sym17101726
- https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366
- OA Status
- gold
- References
- 70
- OpenAlex ID
- https://openalex.org/W4415141632
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415141632Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.3390/sym17101726Digital Object Identifier
- Title
-
Symmetry-Aware Superpixel-Enhanced Few-Shot Semantic SegmentationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-14Full publication date if available
- Authors
-
Lan Guo, Xingran Li, Jinqiang Wang, Yuqi Tong, Jie Xiao, Rui Zhou, Ling-Huey Li, Qingguo Zhou, Kuan‐Ching LiList of authors in order
- Landing page
-
https://doi.org/10.3390/sym17101726Publisher landing page
- PDF URL
-
https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
70Number of works referenced by this work
Full payload
| id | https://openalex.org/W4415141632 |
|---|---|
| doi | https://doi.org/10.3390/sym17101726 |
| ids.doi | https://doi.org/10.3390/sym17101726 |
| ids.openalex | https://openalex.org/W4415141632 |
| fwci | 0.0 |
| type | article |
| title | Symmetry-Aware Superpixel-Enhanced Few-Shot Semantic Segmentation |
| biblio.issue | 10 |
| biblio.volume | 17 |
| biblio.last_page | 1726 |
| biblio.first_page | 1726 |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9990000128746033 |
| 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 | Advanced Neural Network Applications |
| 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 | 0.9940000176429749 |
| 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/T12386 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9901999831199646 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2204 |
| topics[2].subfield.display_name | Biomedical Engineering |
| topics[2].display_name | Advanced X-ray and CT Imaging |
| is_xpac | False |
| apc_list.value | 2000 |
| apc_list.currency | CHF |
| apc_list.value_usd | 2165 |
| apc_paid.value | 2000 |
| apc_paid.currency | CHF |
| apc_paid.value_usd | 2165 |
| language | en |
| locations[0].id | doi:10.3390/sym17101726 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S190787756 |
| locations[0].source.issn | 2073-8994 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2073-8994 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Symmetry |
| locations[0].source.host_organization | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Symmetry |
| locations[0].landing_page_url | https://doi.org/10.3390/sym17101726 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5030410082 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6069-0678 |
| authorships[0].author.display_name | Lan Guo |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[0].institutions[0].id | https://openalex.org/I76214153 |
| authorships[0].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Lanzhou University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lan Guo |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[1].author.id | https://openalex.org/A5070136748 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Xingran Li |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[1].institutions[0].id | https://openalex.org/I76214153 |
| authorships[1].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Lanzhou University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xuyang Li |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[2].author.id | https://openalex.org/A5100783793 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3500-2597 |
| authorships[2].author.display_name | Jinqiang Wang |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[2].institutions[0].id | https://openalex.org/I76214153 |
| authorships[2].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Lanzhou University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Jinqiang Wang |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[3].author.id | https://openalex.org/A5078784955 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Yuqi Tong |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[3].institutions[0].id | https://openalex.org/I76214153 |
| authorships[3].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Lanzhou University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yuqi Tong |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[4].author.id | https://openalex.org/A5045471152 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1433-5437 |
| authorships[4].author.display_name | Jie Xiao |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[4].institutions[0].id | https://openalex.org/I76214153 |
| authorships[4].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Lanzhou University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jie Xiao |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[5].author.id | https://openalex.org/A5114549552 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-9968-6190 |
| authorships[5].author.display_name | Rui Zhou |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[5].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[5].institutions[0].id | https://openalex.org/I76214153 |
| authorships[5].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Lanzhou University |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Rui Zhou |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[6].author.id | https://openalex.org/A5114610971 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Ling-Huey Li |
| authorships[6].countries | TW |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I177918364 |
| authorships[6].affiliations[0].raw_affiliation_string | Department of Computer Science and Information Engineering, Providence University, Taichung 43301, Taiwan |
| authorships[6].institutions[0].id | https://openalex.org/I177918364 |
| authorships[6].institutions[0].ror | https://ror.org/03fcpsq87 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I177918364 |
| authorships[6].institutions[0].country_code | TW |
| authorships[6].institutions[0].display_name | Providence University |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Ling-Huey Li |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Department of Computer Science and Information Engineering, Providence University, Taichung 43301, Taiwan |
| authorships[7].author.id | https://openalex.org/A5113979790 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Qingguo Zhou |
| authorships[7].countries | CN |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I76214153 |
| authorships[7].affiliations[0].raw_affiliation_string | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[7].institutions[0].id | https://openalex.org/I76214153 |
| authorships[7].institutions[0].ror | https://ror.org/01mkqqe32 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I76214153 |
| authorships[7].institutions[0].country_code | CN |
| authorships[7].institutions[0].display_name | Lanzhou University |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Qingguo Zhou |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| authorships[8].author.id | https://openalex.org/A5063188437 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-1381-4364 |
| authorships[8].author.display_name | Kuan‐Ching Li |
| authorships[8].countries | TW |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I177918364 |
| authorships[8].affiliations[0].raw_affiliation_string | Department of Computer Science and Information Engineering, Providence University, Taichung 43301, Taiwan |
| authorships[8].institutions[0].id | https://openalex.org/I177918364 |
| authorships[8].institutions[0].ror | https://ror.org/03fcpsq87 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I177918364 |
| authorships[8].institutions[0].country_code | TW |
| authorships[8].institutions[0].display_name | Providence University |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Kuan-Ching Li |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Department of Computer Science and Information Engineering, Providence University, Taichung 43301, Taiwan |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-14T00:00:00 |
| display_name | Symmetry-Aware Superpixel-Enhanced Few-Shot Semantic Segmentation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9990000128746033 |
| 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 | Advanced Neural Network Applications |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.3390/sym17101726 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S190787756 |
| best_oa_location.source.issn | 2073-8994 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2073-8994 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Symmetry |
| best_oa_location.source.host_organization | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Symmetry |
| best_oa_location.landing_page_url | https://doi.org/10.3390/sym17101726 |
| primary_location.id | doi:10.3390/sym17101726 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S190787756 |
| primary_location.source.issn | 2073-8994 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2073-8994 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Symmetry |
| primary_location.source.host_organization | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_name | Multidisciplinary Digital Publishing Institute |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.mdpi.com/2073-8994/17/10/1726/pdf?version=1760426366 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Symmetry |
| primary_location.landing_page_url | https://doi.org/10.3390/sym17101726 |
| publication_date | 2025-10-14 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4404287555, https://openalex.org/W4392357940, https://openalex.org/W4402753894, https://openalex.org/W4414348659, https://openalex.org/W4401070596, https://openalex.org/W4403182012, https://openalex.org/W4402754281, https://openalex.org/W4405598539, https://openalex.org/W2988205463, https://openalex.org/W2964105864, https://openalex.org/W3169352167, https://openalex.org/W3033502887, https://openalex.org/W2997884746, https://openalex.org/W4408326908, https://openalex.org/W4405907314, https://openalex.org/W4391707549, https://openalex.org/W4391560482, https://openalex.org/W4402435390, https://openalex.org/W4406314479, https://openalex.org/W4406910065, https://openalex.org/W2412782625, https://openalex.org/W2963881378, https://openalex.org/W2560023338, https://openalex.org/W2965391153, https://openalex.org/W3034958977, https://openalex.org/W3159640305, https://openalex.org/W4413123340, https://openalex.org/W4404890824, https://openalex.org/W2963078159, https://openalex.org/W2963599420, https://openalex.org/W4413062386, https://openalex.org/W3154651309, https://openalex.org/W3167559252, https://openalex.org/W3204077273, https://openalex.org/W3176065502, https://openalex.org/W4214893857, https://openalex.org/W4376163385, https://openalex.org/W4391557921, https://openalex.org/W4412652537, https://openalex.org/W4385163296, https://openalex.org/W4312777193, https://openalex.org/W2031489346, https://openalex.org/W2144794286, https://openalex.org/W4214660208, https://openalex.org/W2194775991, https://openalex.org/W4386195362, https://openalex.org/W4307778354, https://openalex.org/W3047258141, https://openalex.org/W4296181602, https://openalex.org/W4390748585, https://openalex.org/W4386245957, https://openalex.org/W3090986860, https://openalex.org/W2981787211, https://openalex.org/W3120893267, https://openalex.org/W4362683490, https://openalex.org/W4387580310, https://openalex.org/W3169024950, https://openalex.org/W3166574225, https://openalex.org/W4360979595, https://openalex.org/W4313180545, https://openalex.org/W1901129140, https://openalex.org/W3140935014, https://openalex.org/W3106906018, https://openalex.org/W3108187451, https://openalex.org/W4318751704, https://openalex.org/W4313196086, https://openalex.org/W3110608229, https://openalex.org/W4410022112, https://openalex.org/W1861492603, https://openalex.org/W3108189450 |
| referenced_works_count | 70 |
| abstract_inverted_index.a | 40, 46, 78, 104 |
| abstract_inverted_index.To | 34 |
| abstract_inverted_index.We | 132 |
| abstract_inverted_index.as | 24 |
| abstract_inverted_index.by | 158 |
| abstract_inverted_index.in | 7, 56 |
| abstract_inverted_index.of | 82 |
| abstract_inverted_index.on | 31, 138, 184 |
| abstract_inverted_index.to | 16, 76, 102, 113, 141, 153, 175 |
| abstract_inverted_index.we | 38, 163 |
| abstract_inverted_index.FSS | 43, 207 |
| abstract_inverted_index.RAG | 140 |
| abstract_inverted_index.and | 11, 28, 60, 70, 88, 97, 145, 148, 167, 179, 187, 202 |
| abstract_inverted_index.are | 93, 111, 118 |
| abstract_inverted_index.due | 15 |
| abstract_inverted_index.for | 125 |
| abstract_inverted_index.our | 192 |
| abstract_inverted_index.the | 53, 58, 122, 139, 151, 154, 172, 185, 200 |
| abstract_inverted_index.both | 57, 177 |
| abstract_inverted_index.cues | 72 |
| abstract_inverted_index.edge | 69 |
| abstract_inverted_index.into | 73, 95, 99, 121 |
| abstract_inverted_index.more | 79 |
| abstract_inverted_index.over | 199 |
| abstract_inverted_index.rely | 29 |
| abstract_inverted_index.seen | 178 |
| abstract_inverted_index.that | 50, 191 |
| abstract_inverted_index.then | 119 |
| abstract_inverted_index.used | 112 |
| abstract_inverted_index.with | 45, 129, 205 |
| abstract_inverted_index.(FSS) | 3 |
| abstract_inverted_index.Graph | 107 |
| abstract_inverted_index.build | 77 |
| abstract_inverted_index.faces | 4 |
| abstract_inverted_index.model | 194 |
| abstract_inverted_index.novel | 180 |
| abstract_inverted_index.pixel | 155 |
| abstract_inverted_index.query | 61 |
| abstract_inverted_index.space | 124 |
| abstract_inverted_index.these | 36 |
| abstract_inverted_index.which | 117 |
| abstract_inverted_index.(RAG). | 108 |
| abstract_inverted_index.First, | 63 |
| abstract_inverted_index.Region | 105 |
| abstract_inverted_index.fusion | 66 |
| abstract_inverted_index.images | 92 |
| abstract_inverted_index.models | 52 |
| abstract_inverted_index.robust | 165 |
| abstract_inverted_index.single | 25 |
| abstract_inverted_index.solely | 30 |
| abstract_inverted_index.space. | 156 |
| abstract_inverted_index.Lastly, | 157 |
| abstract_inverted_index.Second, | 91 |
| abstract_inverted_index.ability | 174 |
| abstract_inverted_index.address | 35 |
| abstract_inverted_index.classes | 27 |
| abstract_inverted_index.complex | 9, 83 |
| abstract_inverted_index.enhance | 142 |
| abstract_inverted_index.finally | 149 |
| abstract_inverted_index.further | 133 |
| abstract_inverted_index.injects | 67 |
| abstract_inverted_index.issues, | 37 |
| abstract_inverted_index.limited | 17 |
| abstract_inverted_index.message | 135 |
| abstract_inverted_index.methods | 21 |
| abstract_inverted_index.perform | 134 |
| abstract_inverted_index.propose | 39 |
| abstract_inverted_index.remains | 203 |
| abstract_inverted_index.support | 59, 130 |
| abstract_inverted_index.texture | 71 |
| abstract_inverted_index.COCO-20i | 188 |
| abstract_inverted_index.Existing | 20 |
| abstract_inverted_index.Few-Shot | 0 |
| abstract_inverted_index.Semantic | 1 |
| abstract_inverted_index.achieves | 195 |
| abstract_inverted_index.baseline | 201 |
| abstract_inverted_index.boundary | 89, 146 |
| abstract_inverted_index.complete | 80 |
| abstract_inverted_index.existing | 206 |
| abstract_inverted_index.methods. | 208 |
| abstract_inverted_index.modeling | 8 |
| abstract_inverted_index.negative | 26 |
| abstract_inverted_index.perceive | 176 |
| abstract_inverted_index.proposed | 193 |
| abstract_inverted_index.quality. | 90 |
| abstract_inverted_index.samples. | 19 |
| abstract_inverted_index.semantic | 161 |
| abstract_inverted_index.superior | 196 |
| abstract_inverted_index.targets. | 181 |
| abstract_inverted_index.training | 18 |
| abstract_inverted_index.Adjacency | 106 |
| abstract_inverted_index.Extensive | 182 |
| abstract_inverted_index.PASCAL-5i | 186 |
| abstract_inverted_index.alignment | 128 |
| abstract_inverted_index.branches. | 62 |
| abstract_inverted_index.construct | 103, 164 |
| abstract_inverted_index.enhancing | 171 |
| abstract_inverted_index.framework | 44 |
| abstract_inverted_index.improving | 85 |
| abstract_inverted_index.low-level | 68 |
| abstract_inverted_index.model’s | 173 |
| abstract_inverted_index.projected | 120 |
| abstract_inverted_index.prototype | 127, 169 |
| abstract_inverted_index.semantics | 75 |
| abstract_inverted_index.symmetric | 47 |
| abstract_inverted_index.tokens” | 101 |
| abstract_inverted_index.adherence, | 147 |
| abstract_inverted_index.aggregated | 98 |
| abstract_inverted_index.background | 168 |
| abstract_inverted_index.benchmarks | 189 |
| abstract_inverted_index.challenges | 6 |
| abstract_inverted_index.explicitly | 51 |
| abstract_inverted_index.foreground | 166 |
| abstract_inverted_index.high-level | 74 |
| abstract_inverted_index.initialize | 114 |
| abstract_inverted_index.prediction | 13 |
| abstract_inverted_index.prototypes | 110 |
| abstract_inverted_index.superpixel | 54, 123 |
| abstract_inverted_index.top–down | 64 |
| abstract_inverted_index.Support-set | 109 |
| abstract_inverted_index.aggregating | 159 |
| abstract_inverted_index.alignments. | 33 |
| abstract_inverted_index.backgrounds | 10, 23 |
| abstract_inverted_index.competitive | 204 |
| abstract_inverted_index.consistency | 14, 144 |
| abstract_inverted_index.cross-image | 126 |
| abstract_inverted_index.cross-layer | 65 |
| abstract_inverted_index.demonstrate | 190 |
| abstract_inverted_index.dual-branch | 48 |
| abstract_inverted_index.experiments | 183 |
| abstract_inverted_index.homogeneous | 160 |
| abstract_inverted_index.maintaining | 12 |
| abstract_inverted_index.partitioned | 94 |
| abstract_inverted_index.performance | 198 |
| abstract_inverted_index.pixel-level | 32 |
| abstract_inverted_index.predictions | 152 |
| abstract_inverted_index.query-pixel | 115 |
| abstract_inverted_index.significant | 5 |
| abstract_inverted_index.superpixels | 96 |
| abstract_inverted_index.Segmentation | 2 |
| abstract_inverted_index.architecture | 49 |
| abstract_inverted_index.back-project | 150 |
| abstract_inverted_index.backgrounds, | 84 |
| abstract_inverted_index.information, | 162 |
| abstract_inverted_index.intra-region | 143 |
| abstract_inverted_index.minimization | 137 |
| abstract_inverted_index.oversimplify | 22 |
| abstract_inverted_index.predictions, | 116 |
| abstract_inverted_index.region-graph | 55 |
| abstract_inverted_index.segmentation | 197 |
| abstract_inverted_index.separability | 87 |
| abstract_inverted_index.superpixels. | 131 |
| abstract_inverted_index.“superpixel | 100 |
| abstract_inverted_index.passing/energy | 136 |
| abstract_inverted_index.representation | 81 |
| abstract_inverted_index.symmetry-aware | 41 |
| abstract_inverted_index.representations, | 170 |
| abstract_inverted_index.superpixel-enhanced | 42 |
| abstract_inverted_index.foreground–background | 86 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile.value | 0.510793 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |