Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948025812> ?p ?o ?g. }
- W2948025812 abstract "We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns the final models using a multi-task classification loss for the source and target domains. Note that the two domains have separate batch normalization layers in both stages. Our framework can be easily incorporated into the domain adaptation techniques based on deep neural networks with batch normalization layers. We also present that our approach can be extended to the problem with multiple source domains. The proposed algorithm is evaluated on multiple benchmark datasets and achieves the state-of-the-art accuracy in the standard setting and the multi-source domain adaption scenario." @default.
- W2948025812 created "2019-06-14" @default.
- W2948025812 creator A5006594639 @default.
- W2948025812 creator A5016098551 @default.
- W2948025812 creator A5030395518 @default.
- W2948025812 creator A5060343759 @default.
- W2948025812 creator A5068063341 @default.
- W2948025812 date "2019-05-27" @default.
- W2948025812 modified "2023-10-16" @default.
- W2948025812 title "Domain-Specific Batch Normalization for Unsupervised Domain Adaptation" @default.
- W2948025812 cites W1565327149 @default.
- W2948025812 cites W1722318740 @default.
- W2948025812 cites W1731081199 @default.
- W2948025812 cites W1836465849 @default.
- W2948025812 cites W1861492603 @default.
- W2948025812 cites W2159291411 @default.
- W2948025812 cites W2164943005 @default.
- W2948025812 cites W2279034837 @default.
- W2948025812 cites W2511131004 @default.
- W2948025812 cites W2593768305 @default.
- W2948025812 cites W2594718649 @default.
- W2948025812 cites W2627183927 @default.
- W2948025812 cites W2766897166 @default.
- W2948025812 cites W2793888044 @default.
- W2948025812 cites W2795155917 @default.
- W2948025812 cites W2797433568 @default.
- W2948025812 cites W2798681837 @default.
- W2948025812 cites W2803297029 @default.
- W2948025812 cites W2950564929 @default.
- W2948025812 cites W2962687275 @default.
- W2948025812 cites W2962808524 @default.
- W2948025812 cites W2963217615 @default.
- W2948025812 cites W2963777311 @default.
- W2948025812 cites W2963864946 @default.
- W2948025812 cites W2963870446 @default.
- W2948025812 cites W2964121744 @default.
- W2948025812 cites W2964139811 @default.
- W2948025812 cites W2964278684 @default.
- W2948025812 cites W2964285681 @default.
- W2948025812 cites W2964288524 @default.
- W2948025812 doi "https://doi.org/10.48550/arxiv.1906.03950" @default.
- W2948025812 hasPublicationYear "2019" @default.
- W2948025812 type Work @default.
- W2948025812 sameAs 2948025812 @default.
- W2948025812 citedByCount "7" @default.
- W2948025812 countsByYear W29480258122020 @default.
- W2948025812 countsByYear W29480258122021 @default.
- W2948025812 crossrefType "posted-content" @default.
- W2948025812 hasAuthorship W2948025812A5006594639 @default.
- W2948025812 hasAuthorship W2948025812A5016098551 @default.
- W2948025812 hasAuthorship W2948025812A5030395518 @default.
- W2948025812 hasAuthorship W2948025812A5060343759 @default.
- W2948025812 hasAuthorship W2948025812A5068063341 @default.
- W2948025812 hasBestOaLocation W29480258121 @default.
- W2948025812 hasConcept C11413529 @default.
- W2948025812 hasConcept C119857082 @default.
- W2948025812 hasConcept C13280743 @default.
- W2948025812 hasConcept C134306372 @default.
- W2948025812 hasConcept C136886441 @default.
- W2948025812 hasConcept C144024400 @default.
- W2948025812 hasConcept C153180895 @default.
- W2948025812 hasConcept C154945302 @default.
- W2948025812 hasConcept C185798385 @default.
- W2948025812 hasConcept C19165224 @default.
- W2948025812 hasConcept C205649164 @default.
- W2948025812 hasConcept C2776434776 @default.
- W2948025812 hasConcept C33923547 @default.
- W2948025812 hasConcept C36503486 @default.
- W2948025812 hasConcept C41008148 @default.
- W2948025812 hasConcept C50644808 @default.
- W2948025812 hasConcept C81363708 @default.
- W2948025812 hasConcept C95623464 @default.
- W2948025812 hasConceptScore W2948025812C11413529 @default.
- W2948025812 hasConceptScore W2948025812C119857082 @default.
- W2948025812 hasConceptScore W2948025812C13280743 @default.
- W2948025812 hasConceptScore W2948025812C134306372 @default.
- W2948025812 hasConceptScore W2948025812C136886441 @default.
- W2948025812 hasConceptScore W2948025812C144024400 @default.
- W2948025812 hasConceptScore W2948025812C153180895 @default.
- W2948025812 hasConceptScore W2948025812C154945302 @default.
- W2948025812 hasConceptScore W2948025812C185798385 @default.
- W2948025812 hasConceptScore W2948025812C19165224 @default.
- W2948025812 hasConceptScore W2948025812C205649164 @default.
- W2948025812 hasConceptScore W2948025812C2776434776 @default.
- W2948025812 hasConceptScore W2948025812C33923547 @default.
- W2948025812 hasConceptScore W2948025812C36503486 @default.
- W2948025812 hasConceptScore W2948025812C41008148 @default.
- W2948025812 hasConceptScore W2948025812C50644808 @default.
- W2948025812 hasConceptScore W2948025812C81363708 @default.
- W2948025812 hasConceptScore W2948025812C95623464 @default.
- W2948025812 hasLocation W29480258121 @default.
- W2948025812 hasOpenAccess W2948025812 @default.
- W2948025812 hasPrimaryLocation W29480258121 @default.
- W2948025812 hasRelatedWork W2016839265 @default.
- W2948025812 hasRelatedWork W2175746458 @default.
- W2948025812 hasRelatedWork W2732542196 @default.
- W2948025812 hasRelatedWork W2767651786 @default.
- W2948025812 hasRelatedWork W2949389737 @default.
- W2948025812 hasRelatedWork W2963556241 @default.
- W2948025812 hasRelatedWork W3018421652 @default.