Relieving Long-tailed Instance Segmentation via Pairwise Class Balance Article Swipe
Yin-Yin He
,
Peizhen Zhang
,
Xiu-Shen Wei
,
Xiangyu Zhang
,
Jian Sun
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.02784
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.02784
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing method as a complement. Experimental results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability. The code and trained models are available at https://github.com/megvii-research/PCB.
Related Topics
Concepts
Pairwise comparison
Computer science
Regularization (linguistics)
Debiasing
Segmentation
Artificial intelligence
Generalization
Class (philosophy)
Machine learning
Benchmark (surveying)
Confusion
Complement (music)
Granularity
Code (set theory)
Pattern recognition (psychology)
Mathematics
Biochemistry
Geodesy
Set (abstract data type)
Chemistry
Geography
Operating system
Cognitive science
Phenotype
Gene
Programming language
Complementation
Mathematical analysis
Psychoanalysis
Psychology
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2201.02784
- https://arxiv.org/pdf/2201.02784
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4221160564
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4221160564Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2201.02784Digital Object Identifier
- Title
-
Relieving Long-tailed Instance Segmentation via Pairwise Class BalanceWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-08Full publication date if available
- Authors
-
Yin-Yin He, Peizhen Zhang, Xiu-Shen Wei, Xiangyu Zhang, Jian SunList of authors in order
- Landing page
-
https://arxiv.org/abs/2201.02784Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2201.02784Direct 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/2201.02784Direct OA link when available
- Concepts
-
Pairwise comparison, Computer science, Regularization (linguistics), Debiasing, Segmentation, Artificial intelligence, Generalization, Class (philosophy), Machine learning, Benchmark (surveying), Confusion, Complement (music), Granularity, Code (set theory), Pattern recognition (psychology), Mathematics, Biochemistry, Geodesy, Set (abstract data type), Chemistry, Geography, Operating system, Cognitive science, Phenotype, Gene, Programming language, Complementation, Mathematical analysis, Psychoanalysis, PsychologyTop 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/W4221160564 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2201.02784 |
| ids.doi | https://doi.org/10.48550/arxiv.2201.02784 |
| ids.openalex | https://openalex.org/W4221160564 |
| fwci | |
| type | preprint |
| title | Relieving Long-tailed Instance Segmentation via Pairwise Class Balance |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12874 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.996999979019165 |
| 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 | Digital Imaging for Blood Diseases |
| topics[1].id | https://openalex.org/T11775 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9883999824523926 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2741 |
| topics[1].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[1].display_name | COVID-19 diagnosis using AI |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9857000112533569 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C184898388 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7926619648933411 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1435712 |
| concepts[0].display_name | Pairwise comparison |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7305567264556885 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776135515 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6786930561065674 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[2].display_name | Regularization (linguistics) |
| concepts[3].id | https://openalex.org/C2779458634 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6662417054176331 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q24963715 |
| concepts[3].display_name | Debiasing |
| concepts[4].id | https://openalex.org/C89600930 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6332705020904541 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1423946 |
| concepts[4].display_name | Segmentation |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5652216076850891 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C177148314 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5408772230148315 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[6].display_name | Generalization |
| concepts[7].id | https://openalex.org/C2777212361 |
| concepts[7].level | 2 |
| concepts[7].score | 0.47544145584106445 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[7].display_name | Class (philosophy) |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.46614232659339905 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C185798385 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4629116654396057 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[9].display_name | Benchmark (surveying) |
| concepts[10].id | https://openalex.org/C2781140086 |
| concepts[10].level | 2 |
| concepts[10].score | 0.44180846214294434 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q557945 |
| concepts[10].display_name | Confusion |
| concepts[11].id | https://openalex.org/C112313634 |
| concepts[11].level | 5 |
| concepts[11].score | 0.434567928314209 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7886648 |
| concepts[11].display_name | Complement (music) |
| concepts[12].id | https://openalex.org/C177774035 |
| concepts[12].level | 2 |
| concepts[12].score | 0.42475077509880066 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1246948 |
| concepts[12].display_name | Granularity |
| concepts[13].id | https://openalex.org/C2776760102 |
| concepts[13].level | 3 |
| concepts[13].score | 0.4135347604751587 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[13].display_name | Code (set theory) |
| concepts[14].id | https://openalex.org/C153180895 |
| concepts[14].level | 2 |
| concepts[14].score | 0.4011126458644867 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[14].display_name | Pattern recognition (psychology) |
| concepts[15].id | https://openalex.org/C33923547 |
| concepts[15].level | 0 |
| concepts[15].score | 0.1597626507282257 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[15].display_name | Mathematics |
| concepts[16].id | https://openalex.org/C55493867 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[16].display_name | Biochemistry |
| concepts[17].id | https://openalex.org/C13280743 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q131089 |
| concepts[17].display_name | Geodesy |
| concepts[18].id | https://openalex.org/C177264268 |
| concepts[18].level | 2 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[18].display_name | Set (abstract data type) |
| concepts[19].id | https://openalex.org/C185592680 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[19].display_name | Chemistry |
| concepts[20].id | https://openalex.org/C205649164 |
| concepts[20].level | 0 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[20].display_name | Geography |
| concepts[21].id | https://openalex.org/C111919701 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[21].display_name | Operating system |
| concepts[22].id | https://openalex.org/C188147891 |
| concepts[22].level | 1 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q147638 |
| concepts[22].display_name | Cognitive science |
| concepts[23].id | https://openalex.org/C127716648 |
| concepts[23].level | 3 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q104053 |
| concepts[23].display_name | Phenotype |
| concepts[24].id | https://openalex.org/C104317684 |
| concepts[24].level | 2 |
| concepts[24].score | 0.0 |
| concepts[24].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[24].display_name | Gene |
| concepts[25].id | https://openalex.org/C199360897 |
| concepts[25].level | 1 |
| concepts[25].score | 0.0 |
| concepts[25].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[25].display_name | Programming language |
| concepts[26].id | https://openalex.org/C188082640 |
| concepts[26].level | 4 |
| concepts[26].score | 0.0 |
| concepts[26].wikidata | https://www.wikidata.org/wiki/Q1780899 |
| concepts[26].display_name | Complementation |
| concepts[27].id | https://openalex.org/C134306372 |
| concepts[27].level | 1 |
| concepts[27].score | 0.0 |
| concepts[27].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[27].display_name | Mathematical analysis |
| concepts[28].id | https://openalex.org/C11171543 |
| concepts[28].level | 1 |
| concepts[28].score | 0.0 |
| concepts[28].wikidata | https://www.wikidata.org/wiki/Q41630 |
| concepts[28].display_name | Psychoanalysis |
| concepts[29].id | https://openalex.org/C15744967 |
| concepts[29].level | 0 |
| concepts[29].score | 0.0 |
| concepts[29].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[29].display_name | Psychology |
| keywords[0].id | https://openalex.org/keywords/pairwise-comparison |
| keywords[0].score | 0.7926619648933411 |
| keywords[0].display_name | Pairwise comparison |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7305567264556885 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/regularization |
| keywords[2].score | 0.6786930561065674 |
| keywords[2].display_name | Regularization (linguistics) |
| keywords[3].id | https://openalex.org/keywords/debiasing |
| keywords[3].score | 0.6662417054176331 |
| keywords[3].display_name | Debiasing |
| keywords[4].id | https://openalex.org/keywords/segmentation |
| keywords[4].score | 0.6332705020904541 |
| keywords[4].display_name | Segmentation |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5652216076850891 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/generalization |
| keywords[6].score | 0.5408772230148315 |
| keywords[6].display_name | Generalization |
| keywords[7].id | https://openalex.org/keywords/class |
| keywords[7].score | 0.47544145584106445 |
| keywords[7].display_name | Class (philosophy) |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.46614232659339905 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/benchmark |
| keywords[9].score | 0.4629116654396057 |
| keywords[9].display_name | Benchmark (surveying) |
| keywords[10].id | https://openalex.org/keywords/confusion |
| keywords[10].score | 0.44180846214294434 |
| keywords[10].display_name | Confusion |
| keywords[11].id | https://openalex.org/keywords/complement |
| keywords[11].score | 0.434567928314209 |
| keywords[11].display_name | Complement (music) |
| keywords[12].id | https://openalex.org/keywords/granularity |
| keywords[12].score | 0.42475077509880066 |
| keywords[12].display_name | Granularity |
| keywords[13].id | https://openalex.org/keywords/code |
| keywords[13].score | 0.4135347604751587 |
| keywords[13].display_name | Code (set theory) |
| keywords[14].id | https://openalex.org/keywords/pattern-recognition |
| keywords[14].score | 0.4011126458644867 |
| keywords[14].display_name | Pattern recognition (psychology) |
| keywords[15].id | https://openalex.org/keywords/mathematics |
| keywords[15].score | 0.1597626507282257 |
| keywords[15].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2201.02784 |
| 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/2201.02784 |
| 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/2201.02784 |
| locations[1].id | doi:10.48550/arxiv.2201.02784 |
| 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.2201.02784 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5012174785 |
| authorships[0].author.orcid | https://orcid.org/0009-0009-0356-4833 |
| authorships[0].author.display_name | Yin-Yin He |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | He, Yin-Yin |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101969377 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6012-8933 |
| authorships[1].author.display_name | Peizhen Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Peizhen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5066964304 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8200-1845 |
| authorships[2].author.display_name | Xiu-Shen Wei |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wei, Xiu-Shen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100362465 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-2138-4608 |
| authorships[3].author.display_name | Xiangyu Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Xiangyu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5118900053 |
| authorships[4].author.orcid | https://orcid.org/0009-0006-9443-4046 |
| authorships[4].author.display_name | Jian Sun |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Sun, Jian |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2201.02784 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Relieving Long-tailed Instance Segmentation via Pairwise Class Balance |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12874 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.996999979019165 |
| 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 | Digital Imaging for Blood Diseases |
| related_works | https://openalex.org/W4362554880, https://openalex.org/W4281684980, https://openalex.org/W4386875279, https://openalex.org/W2171721708, https://openalex.org/W4390963114, https://openalex.org/W3214527415, https://openalex.org/W4287887864, https://openalex.org/W1495104519, https://openalex.org/W4225584739, https://openalex.org/W4293248099 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2201.02784 |
| 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/2201.02784 |
| 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/2201.02784 |
| primary_location.id | pmh:oai:arXiv.org:2201.02784 |
| 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/2201.02784 |
| 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/2201.02784 |
| publication_date | 2022-01-08 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 60, 93, 102, 134, 153 |
| abstract_inverted_index.In | 63 |
| abstract_inverted_index.It | 17 |
| abstract_inverted_index.To | 88 |
| abstract_inverted_index.an | 126 |
| abstract_inverted_index.as | 152 |
| abstract_inverted_index.at | 186 |
| abstract_inverted_index.be | 144 |
| abstract_inverted_index.in | 139 |
| abstract_inverted_index.is | 3, 106, 130 |
| abstract_inverted_index.of | 12, 21, 43 |
| abstract_inverted_index.on | 157 |
| abstract_inverted_index.or | 54 |
| abstract_inverted_index.to | 8, 35, 58, 68, 79, 110, 132, 148 |
| abstract_inverted_index.we | 66, 91 |
| abstract_inverted_index.PCB | 116, 142 |
| abstract_inverted_index.The | 179 |
| abstract_inverted_index.and | 38, 136, 146, 168, 181 |
| abstract_inverted_index.any | 149 |
| abstract_inverted_index.are | 184 |
| abstract_inverted_index.can | 143 |
| abstract_inverted_index.due | 7 |
| abstract_inverted_index.for | 121 |
| abstract_inverted_index.one | 42 |
| abstract_inverted_index.our | 161 |
| abstract_inverted_index.the | 9, 22, 29, 40, 44, 70, 75, 81, 85, 112, 176 |
| abstract_inverted_index.use | 51 |
| abstract_inverted_index."how | 34 |
| abstract_inverted_index.LVIS | 158 |
| abstract_inverted_index.This | 32 |
| abstract_inverted_index.code | 180 |
| abstract_inverted_index.end, | 90 |
| abstract_inverted_index.head | 23 |
| abstract_inverted_index.mean | 55 |
| abstract_inverted_index.most | 45 |
| abstract_inverted_index.one. | 87 |
| abstract_inverted_index.show | 175 |
| abstract_inverted_index.soft | 119 |
| abstract_inverted_index.such | 140 |
| abstract_inverted_index.task | 6 |
| abstract_inverted_index.that | 160 |
| abstract_inverted_index.this | 64, 89 |
| abstract_inverted_index.upon | 101 |
| abstract_inverted_index.(PCB) | 98 |
| abstract_inverted_index.(with | 25 |
| abstract_inverted_index.Class | 96 |
| abstract_inverted_index.Prior | 48 |
| abstract_inverted_index.among | 15 |
| abstract_inverted_index.bells | 167 |
| abstract_inverted_index.bias" | 41 |
| abstract_inverted_index.bias. | 62 |
| abstract_inverted_index.built | 100 |
| abstract_inverted_index.label | 52 |
| abstract_inverted_index.novel | 94 |
| abstract_inverted_index.ones. | 31 |
| abstract_inverted_index.score | 56 |
| abstract_inverted_index.which | 73, 105 |
| abstract_inverted_index.works | 49 |
| abstract_inverted_index.across | 172 |
| abstract_inverted_index.biases | 20 |
| abstract_inverted_index.causes | 18 |
| abstract_inverted_index.coarse | 86 |
| abstract_inverted_index.define | 37 |
| abstract_inverted_index.during | 108, 123 |
| abstract_inverted_index.labels | 120 |
| abstract_inverted_index.mainly | 50 |
| abstract_inverted_index.matrix | 104 |
| abstract_inverted_index.method | 151, 162 |
| abstract_inverted_index.models | 183 |
| abstract_inverted_index.paper, | 65 |
| abstract_inverted_index.played | 147 |
| abstract_inverted_index.severe | 19 |
| abstract_inverted_index.smooth | 137 |
| abstract_inverted_index.tailed | 30 |
| abstract_inverted_index.Balance | 97 |
| abstract_inverted_index.against | 28 |
| abstract_inverted_index.biases, | 83 |
| abstract_inverted_index.carries | 74 |
| abstract_inverted_index.classes | 24 |
| abstract_inverted_index.explore | 67 |
| abstract_inverted_index.extreme | 10 |
| abstract_inverted_index.issues. | 47 |
| abstract_inverted_index.matrix, | 72 |
| abstract_inverted_index.method, | 99 |
| abstract_inverted_index.ongoing | 113 |
| abstract_inverted_index.plugged | 145 |
| abstract_inverted_index.propose | 92 |
| abstract_inverted_index.relieve | 80 |
| abstract_inverted_index.renders | 33 |
| abstract_inverted_index.results | 156, 171 |
| abstract_inverted_index.samples | 14 |
| abstract_inverted_index.support | 133 |
| abstract_inverted_index.trained | 182 |
| abstract_inverted_index.updated | 107 |
| abstract_inverted_index.various | 173 |
| abstract_inverted_index.without | 166 |
| abstract_inverted_index.Besides, | 125 |
| abstract_inverted_index.Pairwise | 95 |
| abstract_inverted_index.Superior | 170 |
| abstract_inverted_index.ability. | 178 |
| abstract_inverted_index.achieves | 163 |
| abstract_inverted_index.classes. | 16 |
| abstract_inverted_index.details, | 78 |
| abstract_inverted_index.excavate | 69 |
| abstract_inverted_index.existing | 150 |
| abstract_inverted_index.indicate | 59 |
| abstract_inverted_index.instance | 1 |
| abstract_inverted_index.learning | 128 |
| abstract_inverted_index.majority | 26 |
| abstract_inverted_index.pairwise | 82 |
| abstract_inverted_index.paradigm | 129 |
| abstract_inverted_index.samples) | 27 |
| abstract_inverted_index.training | 13, 109 |
| abstract_inverted_index.alleviate | 39 |
| abstract_inverted_index.available | 185 |
| abstract_inverted_index.confusion | 71, 103 |
| abstract_inverted_index.developed | 131 |
| abstract_inverted_index.fightback | 118 |
| abstract_inverted_index.generates | 117 |
| abstract_inverted_index.imbalance | 11 |
| abstract_inverted_index.important | 46 |
| abstract_inverted_index.iterative | 127 |
| abstract_inverted_index.training. | 124 |
| abstract_inverted_index.whistles. | 169 |
| abstract_inverted_index.accumulate | 111 |
| abstract_inverted_index.debiasing. | 141 |
| abstract_inverted_index.prediction | 114 |
| abstract_inverted_index.Long-tailed | 0 |
| abstract_inverted_index.challenging | 5 |
| abstract_inverted_index.complement. | 154 |
| abstract_inverted_index.demonstrate | 159 |
| abstract_inverted_index.information | 57 |
| abstract_inverted_index.performance | 165 |
| abstract_inverted_index.progressive | 135 |
| abstract_inverted_index.Experimental | 155 |
| abstract_inverted_index.distribution | 53 |
| abstract_inverted_index.fine-grained | 76 |
| abstract_inverted_index.generalizing | 84 |
| abstract_inverted_index.preferences. | 115 |
| abstract_inverted_index.segmentation | 2 |
| abstract_inverted_index.appropriately | 36 |
| abstract_inverted_index.architectures | 174 |
| abstract_inverted_index.coarse-grained | 61 |
| abstract_inverted_index.generalization | 177 |
| abstract_inverted_index.regularization | 122, 138 |
| abstract_inverted_index.state-of-the-art | 164 |
| abstract_inverted_index.misclassification | 77 |
| abstract_inverted_index.https://github.com/megvii-research/PCB. | 187 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.550000011920929 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |