Weld Defect Cascaded Detection Model Based on Bidirectional Multi-scale Feature Fusion and Shape Pre-classification Article Swipe
Haoying Yang
,
Hongbing Wang
,
Haihua Li
,
Xiaoping Song
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.2355/isijinternational.isijint-2022-035
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.2355/isijinternational.isijint-2022-035
Object detection algorithms like Faster R-CNN have been widely used in the field of industrial defect detection. For weld defect detection, its detection accuracy for some small targets and difficult-to-classify defects is not high. This paper proposes a Cascade R-CNN detection model for weld defects based on bidirectional multi-scale feature fusion and shape pre-classification. There are defects of different sizes in the weld. In order to improve the detection ability of the model for multi-size defects, the model adopts the bidirectional feature pyramid network, in which an extra bottom-up path after the top-down path aggregation network and an extra edge from the original input to output node are added. According to the statistics of the proportion distribution of long and short axes of weld defects, the defects can be divided into two categories: long strip defects with the proportion of about 2:1 and approximate circle defects with a much bigger proportion. Therefore, each cascade detector is connected in parallel with a two-categories classifier for long strip and approximate circle defects and a five-categories classifier for five specific defects, so as to realize the pre-classification of two morphological defects and mine the difference between the two shapes of defects. In order to avoid over fitting caused by small datasets. Firstly, noise is added to augment the data. Then the training samples are expanded by random flip and mirror in the training, and OHEM is introduced to balance the selection of positive and negative samples. The experimental results show that the detection accuracy of the model on small targets and difficult-to-classify defects is significantly improved. The mAP value is increased by about 9.3% compared with the traditional Faster R-CNN and about 3.3% compared with the traditional Cascade R-CNN.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.2355/isijinternational.isijint-2022-035
- https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdf
- OA Status
- gold
- Cited By
- 8
- References
- 28
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4286383374
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4286383374Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.2355/isijinternational.isijint-2022-035Digital Object Identifier
- Title
-
Weld Defect Cascaded Detection Model Based on Bidirectional Multi-scale Feature Fusion and Shape Pre-classificationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-04-22Full publication date if available
- Authors
-
Haoying Yang, Hongbing Wang, Haihua Li, Xiaoping SongList of authors in order
- Landing page
-
https://doi.org/10.2355/isijinternational.isijint-2022-035Publisher landing page
- PDF URL
-
https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdfDirect 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.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdfDirect OA link when available
- Concepts
-
Pattern recognition (psychology), Classifier (UML), Artificial intelligence, Welding, Pyramid (geometry), Computer science, Cascade, Fusion, Feature (linguistics), Engineering, Mathematics, Geometry, Mechanical engineering, Linguistics, Chemical engineering, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
8Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4, 2024: 2, 2023: 1, 2022: 1Per-year citation counts (last 5 years)
- References (count)
-
28Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4286383374 |
|---|---|
| doi | https://doi.org/10.2355/isijinternational.isijint-2022-035 |
| ids.doi | https://doi.org/10.2355/isijinternational.isijint-2022-035 |
| ids.openalex | https://openalex.org/W4286383374 |
| fwci | 0.98919425 |
| type | article |
| title | Weld Defect Cascaded Detection Model Based on Bidirectional Multi-scale Feature Fusion and Shape Pre-classification |
| biblio.issue | 7 |
| biblio.volume | 62 |
| biblio.last_page | 1492 |
| biblio.first_page | 1485 |
| topics[0].id | https://openalex.org/T10834 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2210 |
| topics[0].subfield.display_name | Mechanical Engineering |
| topics[0].display_name | Welding Techniques and Residual Stresses |
| topics[1].id | https://openalex.org/T12169 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.998199999332428 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2210 |
| topics[1].subfield.display_name | Mechanical Engineering |
| topics[1].display_name | Non-Destructive Testing Techniques |
| topics[2].id | https://openalex.org/T12111 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9922000169754028 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2209 |
| topics[2].subfield.display_name | Industrial and Manufacturing Engineering |
| topics[2].display_name | Industrial Vision Systems and Defect Detection |
| is_xpac | False |
| apc_list.value | 93000 |
| apc_list.currency | JPY |
| apc_list.value_usd | 700 |
| apc_paid.value | 93000 |
| apc_paid.currency | JPY |
| apc_paid.value_usd | 700 |
| concepts[0].id | https://openalex.org/C153180895 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6455056071281433 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[0].display_name | Pattern recognition (psychology) |
| concepts[1].id | https://openalex.org/C95623464 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6408156156539917 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1096149 |
| concepts[1].display_name | Classifier (UML) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5977959036827087 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C19474535 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5476450324058533 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q131172 |
| concepts[3].display_name | Welding |
| concepts[4].id | https://openalex.org/C142575187 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5316969156265259 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3358290 |
| concepts[4].display_name | Pyramid (geometry) |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.5128922462463379 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C34146451 |
| concepts[6].level | 2 |
| concepts[6].score | 0.49238717555999756 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5048094 |
| concepts[6].display_name | Cascade |
| concepts[7].id | https://openalex.org/C158525013 |
| concepts[7].level | 2 |
| concepts[7].score | 0.420382559299469 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2593739 |
| concepts[7].display_name | Fusion |
| concepts[8].id | https://openalex.org/C2776401178 |
| concepts[8].level | 2 |
| concepts[8].score | 0.41787731647491455 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[8].display_name | Feature (linguistics) |
| concepts[9].id | https://openalex.org/C127413603 |
| concepts[9].level | 0 |
| concepts[9].score | 0.19032150506973267 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[9].display_name | Engineering |
| concepts[10].id | https://openalex.org/C33923547 |
| concepts[10].level | 0 |
| concepts[10].score | 0.18585234880447388 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[10].display_name | Mathematics |
| concepts[11].id | https://openalex.org/C2524010 |
| concepts[11].level | 1 |
| concepts[11].score | 0.12161800265312195 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[11].display_name | Geometry |
| concepts[12].id | https://openalex.org/C78519656 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[12].display_name | Mechanical engineering |
| concepts[13].id | https://openalex.org/C41895202 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[13].display_name | Linguistics |
| concepts[14].id | https://openalex.org/C42360764 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q83588 |
| concepts[14].display_name | Chemical engineering |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/pattern-recognition |
| keywords[0].score | 0.6455056071281433 |
| keywords[0].display_name | Pattern recognition (psychology) |
| keywords[1].id | https://openalex.org/keywords/classifier |
| keywords[1].score | 0.6408156156539917 |
| keywords[1].display_name | Classifier (UML) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5977959036827087 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/welding |
| keywords[3].score | 0.5476450324058533 |
| keywords[3].display_name | Welding |
| keywords[4].id | https://openalex.org/keywords/pyramid |
| keywords[4].score | 0.5316969156265259 |
| keywords[4].display_name | Pyramid (geometry) |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.5128922462463379 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/cascade |
| keywords[6].score | 0.49238717555999756 |
| keywords[6].display_name | Cascade |
| keywords[7].id | https://openalex.org/keywords/fusion |
| keywords[7].score | 0.420382559299469 |
| keywords[7].display_name | Fusion |
| keywords[8].id | https://openalex.org/keywords/feature |
| keywords[8].score | 0.41787731647491455 |
| keywords[8].display_name | Feature (linguistics) |
| keywords[9].id | https://openalex.org/keywords/engineering |
| keywords[9].score | 0.19032150506973267 |
| keywords[9].display_name | Engineering |
| keywords[10].id | https://openalex.org/keywords/mathematics |
| keywords[10].score | 0.18585234880447388 |
| keywords[10].display_name | Mathematics |
| keywords[11].id | https://openalex.org/keywords/geometry |
| keywords[11].score | 0.12161800265312195 |
| keywords[11].display_name | Geometry |
| language | en |
| locations[0].id | doi:10.2355/isijinternational.isijint-2022-035 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S63511553 |
| locations[0].source.issn | 0915-1559, 1347-5460 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 0915-1559 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | ISIJ International |
| locations[0].source.host_organization | https://openalex.org/P4320800556 |
| locations[0].source.host_organization_name | The Iron and Steel Institute of Japan |
| locations[0].source.host_organization_lineage | https://openalex.org/P4320800556 |
| locations[0].source.host_organization_lineage_names | The Iron and Steel Institute of Japan |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | ISIJ International |
| locations[0].landing_page_url | https://doi.org/10.2355/isijinternational.isijint-2022-035 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5102678613 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Haoying Yang |
| authorships[0].countries | KR, YE |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I118692353, https://openalex.org/I88761825 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer and Communication Engineering, University of Science & Technology |
| authorships[0].institutions[0].id | https://openalex.org/I88761825 |
| authorships[0].institutions[0].ror | https://ror.org/000qzf213 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I88761825 |
| authorships[0].institutions[0].country_code | KR |
| authorships[0].institutions[0].display_name | Korea University of Science and Technology |
| authorships[0].institutions[1].id | https://openalex.org/I118692353 |
| authorships[0].institutions[1].ror | https://ror.org/05bj7sh33 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I118692353 |
| authorships[0].institutions[1].country_code | YE |
| authorships[0].institutions[1].display_name | University of Science and Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Haoying Yang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer and Communication Engineering, University of Science & Technology |
| authorships[1].author.id | https://openalex.org/A5101502901 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6838-4552 |
| authorships[1].author.display_name | Hongbing Wang |
| authorships[1].countries | KR, YE |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I118692353, https://openalex.org/I88761825 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Computer and Communication Engineering, University of Science & Technology |
| authorships[1].institutions[0].id | https://openalex.org/I88761825 |
| authorships[1].institutions[0].ror | https://ror.org/000qzf213 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I88761825 |
| authorships[1].institutions[0].country_code | KR |
| authorships[1].institutions[0].display_name | Korea University of Science and Technology |
| authorships[1].institutions[1].id | https://openalex.org/I118692353 |
| authorships[1].institutions[1].ror | https://ror.org/05bj7sh33 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I118692353 |
| authorships[1].institutions[1].country_code | YE |
| authorships[1].institutions[1].display_name | University of Science and Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hongbing Wang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Computer and Communication Engineering, University of Science & Technology |
| authorships[2].author.id | https://openalex.org/A5101546830 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2658-2750 |
| authorships[2].author.display_name | Haihua Li |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210143857 |
| authorships[2].affiliations[0].raw_affiliation_string | Karamay Vocational and Technical College |
| authorships[2].institutions[0].id | https://openalex.org/I4210143857 |
| authorships[2].institutions[0].ror | https://ror.org/047ytwp82 |
| authorships[2].institutions[0].type | healthcare |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210143857 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Karamay Central Hospital |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Haihua Li |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Karamay Vocational and Technical College |
| authorships[3].author.id | https://openalex.org/A5084044015 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0436-1757 |
| authorships[3].author.display_name | Xiaoping Song |
| authorships[3].affiliations[0].raw_affiliation_string | Xinjiang Tianwei Nondestructive Testing Co., Ltd |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Xiaoping Song |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Xinjiang Tianwei Nondestructive Testing Co., Ltd |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Weld Defect Cascaded Detection Model Based on Bidirectional Multi-scale Feature Fusion and Shape Pre-classification |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10834 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2210 |
| primary_topic.subfield.display_name | Mechanical Engineering |
| primary_topic.display_name | Welding Techniques and Residual Stresses |
| related_works | https://openalex.org/W2563096758, https://openalex.org/W4386053843, https://openalex.org/W3158004940, https://openalex.org/W2546942002, https://openalex.org/W2972035100, https://openalex.org/W2970216048, https://openalex.org/W2167582322, https://openalex.org/W3148519004, https://openalex.org/W2382607599, https://openalex.org/W2742991909 |
| cited_by_count | 8 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 2 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 1 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.2355/isijinternational.isijint-2022-035 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S63511553 |
| best_oa_location.source.issn | 0915-1559, 1347-5460 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 0915-1559 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | ISIJ International |
| best_oa_location.source.host_organization | https://openalex.org/P4320800556 |
| best_oa_location.source.host_organization_name | The Iron and Steel Institute of Japan |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4320800556 |
| best_oa_location.source.host_organization_lineage_names | The Iron and Steel Institute of Japan |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | ISIJ International |
| best_oa_location.landing_page_url | https://doi.org/10.2355/isijinternational.isijint-2022-035 |
| primary_location.id | doi:10.2355/isijinternational.isijint-2022-035 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S63511553 |
| primary_location.source.issn | 0915-1559, 1347-5460 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 0915-1559 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | ISIJ International |
| primary_location.source.host_organization | https://openalex.org/P4320800556 |
| primary_location.source.host_organization_name | The Iron and Steel Institute of Japan |
| primary_location.source.host_organization_lineage | https://openalex.org/P4320800556 |
| primary_location.source.host_organization_lineage_names | The Iron and Steel Institute of Japan |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | https://www.jstage.jst.go.jp/article/isijinternational/62/7/62_ISIJINT-2022-035/_pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | ISIJ International |
| primary_location.landing_page_url | https://doi.org/10.2355/isijinternational.isijint-2022-035 |
| publication_date | 2022-04-22 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W1994750329, https://openalex.org/W3202125569, https://openalex.org/W3036908895, https://openalex.org/W2199263226, https://openalex.org/W2919115771, https://openalex.org/W2952765719, https://openalex.org/W1979804891, https://openalex.org/W3124196589, https://openalex.org/W2969970369, https://openalex.org/W268636586, https://openalex.org/W2147800946, https://openalex.org/W639708223, https://openalex.org/W2963037989, https://openalex.org/W2888929252, https://openalex.org/W4205560314, https://openalex.org/W3138118886, https://openalex.org/W2922005503, https://openalex.org/W2964241181, https://openalex.org/W3034971973, https://openalex.org/W1985037657, https://openalex.org/W2321846114, https://openalex.org/W2775465287, https://openalex.org/W3181224095, https://openalex.org/W2960155470, https://openalex.org/W3182814038, https://openalex.org/W3160727506, https://openalex.org/W2042475180, https://openalex.org/W2088831409 |
| referenced_works_count | 28 |
| abstract_inverted_index.a | 37, 147, 160, 171 |
| abstract_inverted_index.In | 63, 198 |
| abstract_inverted_index.an | 86, 97 |
| abstract_inverted_index.as | 179 |
| abstract_inverted_index.be | 128 |
| abstract_inverted_index.by | 205, 222, 268 |
| abstract_inverted_index.in | 10, 60, 84, 157, 227 |
| abstract_inverted_index.is | 31, 155, 210, 232, 260, 266 |
| abstract_inverted_index.of | 13, 57, 70, 113, 117, 122, 139, 184, 196, 238, 251 |
| abstract_inverted_index.on | 46, 254 |
| abstract_inverted_index.so | 178 |
| abstract_inverted_index.to | 65, 104, 110, 180, 200, 212, 234 |
| abstract_inverted_index.2:1 | 141 |
| abstract_inverted_index.For | 17 |
| abstract_inverted_index.The | 243, 263 |
| abstract_inverted_index.and | 28, 51, 96, 119, 142, 166, 170, 188, 225, 230, 240, 257, 277 |
| abstract_inverted_index.are | 55, 107, 220 |
| abstract_inverted_index.can | 127 |
| abstract_inverted_index.for | 24, 42, 73, 163, 174 |
| abstract_inverted_index.its | 21 |
| abstract_inverted_index.mAP | 264 |
| abstract_inverted_index.not | 32 |
| abstract_inverted_index.the | 11, 61, 67, 71, 76, 79, 91, 101, 111, 114, 125, 137, 182, 190, 193, 214, 217, 228, 236, 248, 252, 273, 282 |
| abstract_inverted_index.two | 131, 185, 194 |
| abstract_inverted_index.3.3% | 279 |
| abstract_inverted_index.9.3% | 270 |
| abstract_inverted_index.OHEM | 231 |
| abstract_inverted_index.Then | 216 |
| abstract_inverted_index.This | 34 |
| abstract_inverted_index.axes | 121 |
| abstract_inverted_index.been | 7 |
| abstract_inverted_index.each | 152 |
| abstract_inverted_index.edge | 99 |
| abstract_inverted_index.five | 175 |
| abstract_inverted_index.flip | 224 |
| abstract_inverted_index.from | 100 |
| abstract_inverted_index.have | 6 |
| abstract_inverted_index.into | 130 |
| abstract_inverted_index.like | 3 |
| abstract_inverted_index.long | 118, 133, 164 |
| abstract_inverted_index.mine | 189 |
| abstract_inverted_index.much | 148 |
| abstract_inverted_index.node | 106 |
| abstract_inverted_index.over | 202 |
| abstract_inverted_index.path | 89, 93 |
| abstract_inverted_index.show | 246 |
| abstract_inverted_index.some | 25 |
| abstract_inverted_index.that | 247 |
| abstract_inverted_index.used | 9 |
| abstract_inverted_index.weld | 18, 43, 123 |
| abstract_inverted_index.with | 136, 146, 159, 272, 281 |
| abstract_inverted_index.R-CNN | 5, 39, 276 |
| abstract_inverted_index.There | 54 |
| abstract_inverted_index.about | 140, 269, 278 |
| abstract_inverted_index.added | 211 |
| abstract_inverted_index.after | 90 |
| abstract_inverted_index.avoid | 201 |
| abstract_inverted_index.based | 45 |
| abstract_inverted_index.data. | 215 |
| abstract_inverted_index.extra | 87, 98 |
| abstract_inverted_index.field | 12 |
| abstract_inverted_index.high. | 33 |
| abstract_inverted_index.input | 103 |
| abstract_inverted_index.model | 41, 72, 77, 253 |
| abstract_inverted_index.noise | 209 |
| abstract_inverted_index.order | 64, 199 |
| abstract_inverted_index.paper | 35 |
| abstract_inverted_index.shape | 52 |
| abstract_inverted_index.short | 120 |
| abstract_inverted_index.sizes | 59 |
| abstract_inverted_index.small | 26, 206, 255 |
| abstract_inverted_index.strip | 134, 165 |
| abstract_inverted_index.value | 265 |
| abstract_inverted_index.weld. | 62 |
| abstract_inverted_index.which | 85 |
| abstract_inverted_index.Faster | 4, 275 |
| abstract_inverted_index.Object | 0 |
| abstract_inverted_index.R-CNN. | 285 |
| abstract_inverted_index.added. | 108 |
| abstract_inverted_index.adopts | 78 |
| abstract_inverted_index.bigger | 149 |
| abstract_inverted_index.caused | 204 |
| abstract_inverted_index.circle | 144, 168 |
| abstract_inverted_index.defect | 15, 19 |
| abstract_inverted_index.fusion | 50 |
| abstract_inverted_index.mirror | 226 |
| abstract_inverted_index.output | 105 |
| abstract_inverted_index.random | 223 |
| abstract_inverted_index.shapes | 195 |
| abstract_inverted_index.widely | 8 |
| abstract_inverted_index.Cascade | 38, 284 |
| abstract_inverted_index.ability | 69 |
| abstract_inverted_index.augment | 213 |
| abstract_inverted_index.balance | 235 |
| abstract_inverted_index.between | 192 |
| abstract_inverted_index.cascade | 153 |
| abstract_inverted_index.defects | 30, 44, 56, 126, 135, 145, 169, 187, 259 |
| abstract_inverted_index.divided | 129 |
| abstract_inverted_index.feature | 49, 81 |
| abstract_inverted_index.fitting | 203 |
| abstract_inverted_index.improve | 66 |
| abstract_inverted_index.network | 95 |
| abstract_inverted_index.pyramid | 82 |
| abstract_inverted_index.realize | 181 |
| abstract_inverted_index.results | 245 |
| abstract_inverted_index.samples | 219 |
| abstract_inverted_index.targets | 27, 256 |
| abstract_inverted_index.Firstly, | 208 |
| abstract_inverted_index.accuracy | 23, 250 |
| abstract_inverted_index.compared | 271, 280 |
| abstract_inverted_index.defects, | 75, 124, 177 |
| abstract_inverted_index.defects. | 197 |
| abstract_inverted_index.detector | 154 |
| abstract_inverted_index.expanded | 221 |
| abstract_inverted_index.negative | 241 |
| abstract_inverted_index.network, | 83 |
| abstract_inverted_index.original | 102 |
| abstract_inverted_index.parallel | 158 |
| abstract_inverted_index.positive | 239 |
| abstract_inverted_index.proposes | 36 |
| abstract_inverted_index.samples. | 242 |
| abstract_inverted_index.specific | 176 |
| abstract_inverted_index.top-down | 92 |
| abstract_inverted_index.training | 218 |
| abstract_inverted_index.According | 109 |
| abstract_inverted_index.bottom-up | 88 |
| abstract_inverted_index.connected | 156 |
| abstract_inverted_index.datasets. | 207 |
| abstract_inverted_index.detection | 1, 22, 40, 68, 249 |
| abstract_inverted_index.different | 58 |
| abstract_inverted_index.improved. | 262 |
| abstract_inverted_index.increased | 267 |
| abstract_inverted_index.selection | 237 |
| abstract_inverted_index.training, | 229 |
| abstract_inverted_index.Therefore, | 151 |
| abstract_inverted_index.algorithms | 2 |
| abstract_inverted_index.classifier | 162, 173 |
| abstract_inverted_index.detection, | 20 |
| abstract_inverted_index.detection. | 16 |
| abstract_inverted_index.difference | 191 |
| abstract_inverted_index.industrial | 14 |
| abstract_inverted_index.introduced | 233 |
| abstract_inverted_index.multi-size | 74 |
| abstract_inverted_index.proportion | 115, 138 |
| abstract_inverted_index.statistics | 112 |
| abstract_inverted_index.aggregation | 94 |
| abstract_inverted_index.approximate | 143, 167 |
| abstract_inverted_index.categories: | 132 |
| abstract_inverted_index.multi-scale | 48 |
| abstract_inverted_index.proportion. | 150 |
| abstract_inverted_index.traditional | 274, 283 |
| abstract_inverted_index.distribution | 116 |
| abstract_inverted_index.experimental | 244 |
| abstract_inverted_index.bidirectional | 47, 80 |
| abstract_inverted_index.morphological | 186 |
| abstract_inverted_index.significantly | 261 |
| abstract_inverted_index.two-categories | 161 |
| abstract_inverted_index.five-categories | 172 |
| abstract_inverted_index.pre-classification | 183 |
| abstract_inverted_index.pre-classification. | 53 |
| abstract_inverted_index.difficult-to-classify | 29, 258 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 3 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.68492562 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |