Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987283559> ?p ?o ?g. }
- W2987283559 abstract "We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks." @default.
- W2987283559 created "2019-11-22" @default.
- W2987283559 creator A5018369948 @default.
- W2987283559 creator A5022792966 @default.
- W2987283559 creator A5024785349 @default.
- W2987283559 creator A5049098969 @default.
- W2987283559 creator A5049246408 @default.
- W2987283559 date "2019-11-13" @default.
- W2987283559 modified "2023-09-30" @default.
- W2987283559 title "Momentum Contrast for Unsupervised Visual Representation Learning" @default.
- W2987283559 cites W1536680647 @default.
- W2987283559 cites W1836465849 @default.
- W2987283559 cites W1861492603 @default.
- W2987283559 cites W1903029394 @default.
- W2987283559 cites W1976921161 @default.
- W2987283559 cites W2025768430 @default.
- W2987283559 cites W2031489346 @default.
- W2987283559 cites W2099471712 @default.
- W2987283559 cites W2102605133 @default.
- W2987283559 cites W2108598243 @default.
- W2987283559 cites W2131846894 @default.
- W2987283559 cites W2138621090 @default.
- W2987283559 cites W2144794286 @default.
- W2987283559 cites W2147800946 @default.
- W2987283559 cites W2148349024 @default.
- W2987283559 cites W2152790380 @default.
- W2987283559 cites W2184852195 @default.
- W2987283559 cites W219040644 @default.
- W2987283559 cites W2194775991 @default.
- W2987283559 cites W2250384498 @default.
- W2987283559 cites W2302255633 @default.
- W2987283559 cites W2321533354 @default.
- W2987283559 cites W2326925005 @default.
- W2987283559 cites W2342877626 @default.
- W2987283559 cites W2549139847 @default.
- W2987283559 cites W2558661413 @default.
- W2987283559 cites W2565639579 @default.
- W2987283559 cites W2575671312 @default.
- W2987283559 cites W2613718673 @default.
- W2987283559 cites W2622263826 @default.
- W2987283559 cites W2785694322 @default.
- W2987283559 cites W2798991696 @default.
- W2987283559 cites W2799269579 @default.
- W2987283559 cites W2842511635 @default.
- W2987283559 cites W2883725317 @default.
- W2987283559 cites W2887997457 @default.
- W2987283559 cites W2913939497 @default.
- W2987283559 cites W2933502442 @default.
- W2987283559 cites W2944828972 @default.
- W2987283559 cites W2948012107 @default.
- W2987283559 cites W2948672349 @default.
- W2987283559 cites W2949517790 @default.
- W2987283559 cites W2952865063 @default.
- W2987283559 cites W2953139137 @default.
- W2987283559 cites W2962742544 @default.
- W2987283559 cites W2962835968 @default.
- W2987283559 cites W2963016543 @default.
- W2987283559 cites W2963265008 @default.
- W2987283559 cites W2963341956 @default.
- W2987283559 cites W2963684275 @default.
- W2987283559 cites W2970241862 @default.
- W2987283559 cites W2987741655 @default.
- W2987283559 cites W2990873191 @default.
- W2987283559 cites W2991391304 @default.
- W2987283559 cites W2998388430 @default.
- W2987283559 cites W3005680577 @default.
- W2987283559 cites W3009561768 @default.
- W2987283559 cites W343636949 @default.
- W2987283559 doi "https://doi.org/10.48550/arxiv.1911.05722" @default.
- W2987283559 hasPublicationYear "2019" @default.
- W2987283559 type Work @default.
- W2987283559 sameAs 2987283559 @default.
- W2987283559 citedByCount "237" @default.
- W2987283559 countsByYear W29872835592018 @default.
- W2987283559 countsByYear W29872835592019 @default.
- W2987283559 countsByYear W29872835592020 @default.
- W2987283559 countsByYear W29872835592021 @default.
- W2987283559 countsByYear W29872835592022 @default.
- W2987283559 countsByYear W29872835592023 @default.
- W2987283559 crossrefType "posted-content" @default.
- W2987283559 hasAuthorship W2987283559A5018369948 @default.
- W2987283559 hasAuthorship W2987283559A5022792966 @default.
- W2987283559 hasAuthorship W2987283559A5024785349 @default.
- W2987283559 hasAuthorship W2987283559A5049098969 @default.
- W2987283559 hasAuthorship W2987283559A5049246408 @default.
- W2987283559 hasBestOaLocation W29872835591 @default.
- W2987283559 hasConcept C111919701 @default.
- W2987283559 hasConcept C118505674 @default.
- W2987283559 hasConcept C119857082 @default.
- W2987283559 hasConcept C12713177 @default.
- W2987283559 hasConcept C153180895 @default.
- W2987283559 hasConcept C154945302 @default.
- W2987283559 hasConcept C17744445 @default.
- W2987283559 hasConcept C199360897 @default.
- W2987283559 hasConcept C199539241 @default.
- W2987283559 hasConcept C204321447 @default.
- W2987283559 hasConcept C2776359362 @default.
- W2987283559 hasConcept C2776502983 @default.
- W2987283559 hasConcept C41008148 @default.
- W2987283559 hasConcept C59404180 @default.