Metraipolis › archive › dc_af074ed26481
Hard negative mining — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Hard_negative_mining
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-07T18:21:50.306Z
- SHA-256 of the archived text
a78621d2e71314cd2489a929441326d713580a91b0fed0faebeef662e6c68871- Stable URL of this page
https://metraipolis.com/documento/dc_af074ed26481
How to cite
Hard negative mining — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Hard_negative_mining (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_af074ed26481 (Metraipolis archive dc_af074ed26481, sha256 a78621d2e71314cd2489a929441326d713580a91b0fed0faebeef662e6c68871)
BibTeX
@misc{dcaf074ed26481,
title = {Hard negative mining — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Hard_negative_mining},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_af074ed26481; sha256 a78621d2e71314cd2489a929441326d713580a91b0fed0faebeef662e6c68871},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Hard_negative_mining. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hard negative mining, also referred to as hard negative sampling, is a family of techniques in machine learning for selecting or constructing negative samples more difficult to distinguish from a corresponding positive example with respect to uniformly-sampled negatives, leading to a more informative training signal for discriminative classifiers and similarity models. The technique is used when the pool of possible negative examples is far larger than the set of positives and most randomly chosen negatives are easy to classify by the model, contributing little to learning. Concentrating training on the small fraction of difficult negatives is intended to provide stronger gradient signal and faster convergence than uniform sampling. Hard negative mining originated in object detection in the 1990s, where it was referred to as bootstrapping (not to be confused with statistical bootstrap resampling), and was later formalized for support vector machine models. Closely related ideas appear in deep metric learning, information retrieval, recommender systems, self-supervised contrastive learning, and vision-language models. Surveys distinguish hard negative mining from the broader practice of negative sampling, in which negatives are drawn at random or in proportion to frequency rather than by difficulty. Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «information retrieval»). Fonte: Wikipedia in inglese, voce «Hard negative mining» — https://en.wikipedia.org/wiki/Hard_negative_mining Wikidata Q140419322 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q140419322 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Hard_negative_mining?action=history). Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza. Estratto dell'introduzione non modificato nel contenuto; revisione 1375966014, consultata il 2026-10-07T17:52:14.335Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 200948f295e1b76f60e3ff984c6df671c9ac201ca8200c6a6434cf867b7138aa