CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images Article Swipe
Sheng Guo
,
Weilin Huang
,
Haozhi Zhang
,
Chenfan Zhuang
,
Dengke Dong
,
Matthew R. Scott
,
Ding-Long Huang
·
YOU?
·
· 2018
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1808.01097
YOU?
·
· 2018
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1808.01097
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning, with the goal of handling a massive amount of noisy labels and data imbalance effectively. We design a new learning curriculum by measuring the complexity of data using its distribution density in a feature space, and rank the complexity in an unsupervised manner. This allows for an efficient implementation of curriculum learning on large-scale web images, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially. Importantly, we show by experiments that those images with highly noisy labels can surprisingly improve the generalization capability of the model, by serving as a manner of regularization. Our approaches obtain state-of-the-art performance on four benchmarks: WebVision, ImageNet, Clothing-1M and Food-101. With an ensemble of multiple models, we achieved a top-5 error rate of 5.2% on the WebVision challenge for 1000-category classification. This result was the top performance by a wide margin, outperforming second place by a nearly 50% relative error rate. Code and models are available at: https://github.com/MalongTech/CurriculumNet .
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/1808.01097
- https://arxiv.org/pdf/1808.01097
- OA Status
- green
- Cited By
- 21
- References
- 27
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W2952051629
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2952051629Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.1808.01097Digital Object Identifier
- Title
-
CurriculumNet: Weakly Supervised Learning from Large-Scale Web ImagesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2018Year of publication
- Publication date
-
2018-08-03Full publication date if available
- Authors
-
Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, Ding-Long HuangList of authors in order
- Landing page
-
https://arxiv.org/abs/1808.01097Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/1808.01097Direct 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/1808.01097Direct OA link when available
- Concepts
-
Computer science, Artificial intelligence, Regularization (linguistics), Machine learning, Annotation, Margin (machine learning), Feature learning, Code (set theory), Feature (linguistics), Deep learning, Source code, Linguistics, Philosophy, Operating system, Set (abstract data type), Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
21Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 7, 2020: 8, 2019: 6Per-year citation counts (last 5 years)
- References (count)
-
27Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2952051629 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.1808.01097 |
| ids.doi | https://doi.org/10.48550/arxiv.1808.01097 |
| ids.mag | 2952051629 |
| ids.openalex | https://openalex.org/W2952051629 |
| fwci | |
| type | preprint |
| title | CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12535 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991000294685364 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Machine Learning and Data Classification |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9904000163078308 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9902999997138977 |
| 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 | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8226362466812134 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.6258910894393921 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C2776135515 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5822126865386963 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[2].display_name | Regularization (linguistics) |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5628108978271484 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C2776321320 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4925449788570404 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q857525 |
| concepts[4].display_name | Annotation |
| concepts[5].id | https://openalex.org/C774472 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4552061855792999 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q6760393 |
| concepts[5].display_name | Margin (machine learning) |
| concepts[6].id | https://openalex.org/C59404180 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4409744143486023 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[6].display_name | Feature learning |
| concepts[7].id | https://openalex.org/C2776760102 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4243672788143158 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[7].display_name | Code (set theory) |
| concepts[8].id | https://openalex.org/C2776401178 |
| concepts[8].level | 2 |
| concepts[8].score | 0.42330437898635864 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[8].display_name | Feature (linguistics) |
| concepts[9].id | https://openalex.org/C108583219 |
| concepts[9].level | 2 |
| concepts[9].score | 0.41650086641311646 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[9].display_name | Deep learning |
| concepts[10].id | https://openalex.org/C43126263 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4109400510787964 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q128751 |
| concepts[10].display_name | Source code |
| concepts[11].id | https://openalex.org/C41895202 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[11].display_name | Linguistics |
| concepts[12].id | https://openalex.org/C138885662 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[12].display_name | Philosophy |
| concepts[13].id | https://openalex.org/C111919701 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[13].display_name | Operating system |
| concepts[14].id | https://openalex.org/C177264268 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[14].display_name | Set (abstract data type) |
| concepts[15].id | https://openalex.org/C199360897 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[15].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8226362466812134 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.6258910894393921 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/regularization |
| keywords[2].score | 0.5822126865386963 |
| keywords[2].display_name | Regularization (linguistics) |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.5628108978271484 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/annotation |
| keywords[4].score | 0.4925449788570404 |
| keywords[4].display_name | Annotation |
| keywords[5].id | https://openalex.org/keywords/margin |
| keywords[5].score | 0.4552061855792999 |
| keywords[5].display_name | Margin (machine learning) |
| keywords[6].id | https://openalex.org/keywords/feature-learning |
| keywords[6].score | 0.4409744143486023 |
| keywords[6].display_name | Feature learning |
| keywords[7].id | https://openalex.org/keywords/code |
| keywords[7].score | 0.4243672788143158 |
| keywords[7].display_name | Code (set theory) |
| keywords[8].id | https://openalex.org/keywords/feature |
| keywords[8].score | 0.42330437898635864 |
| keywords[8].display_name | Feature (linguistics) |
| keywords[9].id | https://openalex.org/keywords/deep-learning |
| keywords[9].score | 0.41650086641311646 |
| keywords[9].display_name | Deep learning |
| keywords[10].id | https://openalex.org/keywords/source-code |
| keywords[10].score | 0.4109400510787964 |
| keywords[10].display_name | Source code |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:1808.01097 |
| 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/1808.01097 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/1808.01097 |
| locations[1].id | doi:10.48550/arxiv.1808.01097 |
| 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.1808.01097 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100752605 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8959-2473 |
| authorships[0].author.display_name | Sheng Guo |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[0].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[0].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[0].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Sheng Guo |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[1].author.id | https://openalex.org/A5101909917 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1520-4140 |
| authorships[1].author.display_name | Weilin Huang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[1].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[1].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[1].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Weilin Huang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[2].author.id | https://openalex.org/A5101480431 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Haozhi Zhang |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[2].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[2].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[2].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Haozhi Zhang |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[3].author.id | https://openalex.org/A5109294072 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Chenfan Zhuang |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[3].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[3].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[3].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[3].institutions[0].type | company |
| authorships[3].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Chenfan Zhuang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[4].author.id | https://openalex.org/A5013824768 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Dengke Dong |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[4].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[4].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[4].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[4].institutions[0].type | company |
| authorships[4].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Dengke Dong |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[5].author.id | https://openalex.org/A5019329248 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-1404-4437 |
| authorships[5].author.display_name | Matthew R. Scott |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[5].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[5].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[5].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[5].institutions[0].type | company |
| authorships[5].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Matthew R. Scott |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| authorships[6].author.id | https://openalex.org/A5065095644 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Ding-Long Huang |
| authorships[6].countries | CN |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I4210149914 |
| authorships[6].affiliations[0].raw_affiliation_string | Malong Technologies, Shenzhen, China |
| authorships[6].institutions[0].id | https://openalex.org/I4210149914 |
| authorships[6].institutions[0].ror | https://ror.org/03rjyvk34 |
| authorships[6].institutions[0].type | company |
| authorships[6].institutions[0].lineage | https://openalex.org/I4210149914 |
| authorships[6].institutions[0].country_code | CN |
| authorships[6].institutions[0].display_name | MSIGHT Technologies (China) |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Dinglong Huang |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Malong Technologies, Shenzhen, China |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/1808.01097 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12535 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991000294685364 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Machine Learning and Data Classification |
| related_works | https://openalex.org/W2361861616, https://openalex.org/W2263699433, https://openalex.org/W2377979023, https://openalex.org/W2218034408, https://openalex.org/W2392921965, https://openalex.org/W2358755282, https://openalex.org/W2625833328, https://openalex.org/W1533177136, https://openalex.org/W4380994516, https://openalex.org/W2251519152 |
| cited_by_count | 21 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2020 |
| counts_by_year[1].cited_by_count | 8 |
| counts_by_year[2].year | 2019 |
| counts_by_year[2].cited_by_count | 6 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:1808.01097 |
| 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/1808.01097 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/1808.01097 |
| primary_location.id | pmh:oai:arXiv.org:1808.01097 |
| 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/1808.01097 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/1808.01097 |
| publication_date | 2018-08-03 |
| publication_year | 2018 |
| referenced_works | https://openalex.org/W2952865063, https://openalex.org/W2122457239, https://openalex.org/W2296073425, https://openalex.org/W2963420686, https://openalex.org/W3100570787, https://openalex.org/W2963028646, https://openalex.org/W2194775991, https://openalex.org/W2743473392, https://openalex.org/W2964292098, https://openalex.org/W2613718673, https://openalex.org/W2743200750, https://openalex.org/W12634471, https://openalex.org/W2962749380, https://openalex.org/W2756716612, https://openalex.org/W2949117887, https://openalex.org/W1903029394, https://openalex.org/W1861492603, https://openalex.org/W2952927437, https://openalex.org/W2775306753, https://openalex.org/W2949847866, https://openalex.org/W2618574054, https://openalex.org/W2136504847, https://openalex.org/W2289772031, https://openalex.org/W2274287116, https://openalex.org/W2183341477, https://openalex.org/W1686810756, https://openalex.org/W2614679850 |
| referenced_works_count | 27 |
| abstract_inverted_index.. | 204 |
| abstract_inverted_index.a | 2, 35, 48, 60, 75, 101, 139, 164, 184, 191 |
| abstract_inverted_index.We | 0, 33, 58 |
| abstract_inverted_index.an | 83, 89, 157 |
| abstract_inverted_index.as | 138 |
| abstract_inverted_index.by | 25, 39, 64, 118, 136, 183, 190 |
| abstract_inverted_index.in | 74, 82, 100 |
| abstract_inverted_index.is | 112 |
| abstract_inverted_index.of | 8, 46, 51, 68, 92, 109, 133, 141, 159, 168 |
| abstract_inverted_index.on | 13, 95, 148, 170 |
| abstract_inverted_index.we | 116, 162 |
| abstract_inverted_index.50% | 193 |
| abstract_inverted_index.CNN | 103 |
| abstract_inverted_index.Our | 143 |
| abstract_inverted_index.and | 54, 78, 154, 198 |
| abstract_inverted_index.any | 30 |
| abstract_inverted_index.are | 19, 200 |
| abstract_inverted_index.at: | 202 |
| abstract_inverted_index.can | 127 |
| abstract_inverted_index.for | 88, 174 |
| abstract_inverted_index.its | 71 |
| abstract_inverted_index.new | 61 |
| abstract_inverted_index.raw | 21 |
| abstract_inverted_index.the | 23, 44, 66, 80, 106, 130, 134, 171, 180 |
| abstract_inverted_index.top | 181 |
| abstract_inverted_index.was | 179 |
| abstract_inverted_index.web | 16, 97 |
| abstract_inverted_index.yet | 4 |
| abstract_inverted_index.5.2% | 169 |
| abstract_inverted_index.Code | 197 |
| abstract_inverted_index.This | 86, 177 |
| abstract_inverted_index.With | 156 |
| abstract_inverted_index.data | 55, 69 |
| abstract_inverted_index.deep | 10 |
| abstract_inverted_index.four | 149 |
| abstract_inverted_index.from | 22 |
| abstract_inverted_index.goal | 45 |
| abstract_inverted_index.rank | 79 |
| abstract_inverted_index.rate | 167 |
| abstract_inverted_index.show | 117 |
| abstract_inverted_index.text | 27 |
| abstract_inverted_index.that | 120 |
| abstract_inverted_index.wide | 185 |
| abstract_inverted_index.with | 43, 123 |
| abstract_inverted_index.error | 166, 195 |
| abstract_inverted_index.human | 31 |
| abstract_inverted_index.noisy | 52, 110, 125 |
| abstract_inverted_index.place | 189 |
| abstract_inverted_index.rate. | 196 |
| abstract_inverted_index.those | 121 |
| abstract_inverted_index.top-5 | 165 |
| abstract_inverted_index.using | 26, 70 |
| abstract_inverted_index.where | 105 |
| abstract_inverted_index.which | 18 |
| abstract_inverted_index.allows | 87 |
| abstract_inverted_index.amount | 50 |
| abstract_inverted_index.design | 59 |
| abstract_inverted_index.highly | 124 |
| abstract_inverted_index.images | 122 |
| abstract_inverted_index.impact | 108 |
| abstract_inverted_index.labels | 53, 111, 126 |
| abstract_inverted_index.manner | 140 |
| abstract_inverted_index.model, | 104, 135 |
| abstract_inverted_index.models | 199 |
| abstract_inverted_index.nearly | 192 |
| abstract_inverted_index.neural | 11 |
| abstract_inverted_index.obtain | 145 |
| abstract_inverted_index.result | 178 |
| abstract_inverted_index.second | 188 |
| abstract_inverted_index.simple | 3 |
| abstract_inverted_index.space, | 77 |
| abstract_inverted_index.capable | 7 |
| abstract_inverted_index.crawled | 20 |
| abstract_inverted_index.density | 73 |
| abstract_inverted_index.develop | 34 |
| abstract_inverted_index.feature | 76 |
| abstract_inverted_index.images, | 17, 98 |
| abstract_inverted_index.improve | 129 |
| abstract_inverted_index.manner. | 85 |
| abstract_inverted_index.margin, | 186 |
| abstract_inverted_index.massive | 49 |
| abstract_inverted_index.models, | 161 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.reduced | 113 |
| abstract_inverted_index.serving | 137 |
| abstract_inverted_index.without | 29 |
| abstract_inverted_index.Internet | 24 |
| abstract_inverted_index.achieved | 163 |
| abstract_inverted_index.approach | 6 |
| abstract_inverted_index.ensemble | 158 |
| abstract_inverted_index.handling | 47 |
| abstract_inverted_index.learning | 37, 62, 94 |
| abstract_inverted_index.multiple | 160 |
| abstract_inverted_index.negative | 107 |
| abstract_inverted_index.networks | 12 |
| abstract_inverted_index.queries, | 28 |
| abstract_inverted_index.relative | 194 |
| abstract_inverted_index.strategy | 38 |
| abstract_inverted_index.training | 9 |
| abstract_inverted_index.Food-101. | 155 |
| abstract_inverted_index.ImageNet, | 152 |
| abstract_inverted_index.WebVision | 172 |
| abstract_inverted_index.available | 201 |
| abstract_inverted_index.challenge | 173 |
| abstract_inverted_index.efficient | 5, 90 |
| abstract_inverted_index.imbalance | 56 |
| abstract_inverted_index.learning, | 42 |
| abstract_inverted_index.measuring | 65 |
| abstract_inverted_index.resulting | 99 |
| abstract_inverted_index.WebVision, | 151 |
| abstract_inverted_index.approaches | 144 |
| abstract_inverted_index.capability | 132 |
| abstract_inverted_index.complexity | 67, 81 |
| abstract_inverted_index.curriculum | 41, 63, 93 |
| abstract_inverted_index.leveraging | 40 |
| abstract_inverted_index.principled | 36 |
| abstract_inverted_index.Clothing-1M | 153 |
| abstract_inverted_index.annotation. | 32 |
| abstract_inverted_index.benchmarks: | 150 |
| abstract_inverted_index.experiments | 119 |
| abstract_inverted_index.large-scale | 14, 96 |
| abstract_inverted_index.performance | 147, 182 |
| abstract_inverted_index.Importantly, | 115 |
| abstract_inverted_index.distribution | 72 |
| abstract_inverted_index.effectively. | 57 |
| abstract_inverted_index.surprisingly | 128 |
| abstract_inverted_index.unsupervised | 84 |
| abstract_inverted_index.1000-category | 175 |
| abstract_inverted_index.outperforming | 187 |
| abstract_inverted_index.generalization | 131 |
| abstract_inverted_index.implementation | 91 |
| abstract_inverted_index.substantially. | 114 |
| abstract_inverted_index.classification. | 176 |
| abstract_inverted_index.regularization. | 142 |
| abstract_inverted_index.high-performance | 102 |
| abstract_inverted_index.state-of-the-art | 146 |
| abstract_inverted_index.weakly-supervised | 15 |
| abstract_inverted_index.https://github.com/MalongTech/CurriculumNet | 203 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |