Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Kaiming He · Shaoqing Ren
- Dates
- Published 2015 authorship evidence authorship evidence
- Exact source
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification arXiv · published 2015-02-06 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 8df408d4e1b0e70f93ffd1773b8e6cdff9378ede9ba1656d6d4d5ad595b09ddb). Submission history as arXiv records it (UTC): v1 6 February 2015. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Crossref · published 2015 · Crossref record of the conference version: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026-1034 (DOI 10.1109/iccv.2015.123), retrieved for the candidate pack on 2026-10-28. The date is the publisher-deposited date, kept at year precision; it was not checked against the issue.
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification arXiv · published 2015-02-06 · arXiv:1502.01852v1, submitted 6 February 2015 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 738cb88db1250d9bdbf51569c5ec3a87303c7e946167d58381003d2f93d4127d). The author list is the byline as printed on the first page.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
- Author: Kaiming HeKaiming He is a credited author of Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.2015 · publication · Stated in source · Supported Inspect claim & evidence ↗Kaiming He: person page →
- Author: Shaoqing RenShaoqing Ren is a credited author of Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.2015 · publication · Stated in source · Supported Inspect claim & evidence ↗Shaoqing Ren: person page →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document says it adds
The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.
- In its own wordsThe paper proposes a Parametric Rectified Linear Unit (PReLU) that generalises the traditional rectified unit.“First, we propose a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit.” arXiv v1, PDF p. 1, abstract2015-02-06 · publication · Stated in source · Supported Inspect claim & evidence ↗
- In its own words · includes its own priority claimThe paper states that, to the authors’ knowledge, its result on ImageNet 2012 classification is the first to surpass the human-level performance figure of 5.1% it cites for this challenge.“To our knowledge, our result is the first to surpass human-level performance (5.1%, [22]) on this visual recognition challenge.” arXiv v1, PDF p. 1, abstract2015-02-06 · publication · Stated in source · Supported Inspect claim & evidence ↗