Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167014763> ?p ?o ?g. }
- W3167014763 abstract "Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on this finding, we further investigate whether SSL methods work on UDA tasks. By adapting eight representative SSL algorithms on UDA benchmarks, we show that SSL methods are strong UDA learners. Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques. We thus promote that SSL methods should be employed as baselines in future UDA studies and expect that the revealed relationship between UDA and SSL could shed light on future UDA development. Codes are available at url{this https URL}." @default.
- W3167014763 created "2021-06-22" @default.
- W3167014763 creator A5016991275 @default.
- W3167014763 creator A5040092039 @default.
- W3167014763 creator A5065912071 @default.
- W3167014763 creator A5065964089 @default.
- W3167014763 creator A5087859582 @default.
- W3167014763 creator A5091460874 @default.
- W3167014763 date "2021-06-01" @default.
- W3167014763 modified "2023-09-26" @default.
- W3167014763 title "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners" @default.
- W3167014763 cites W1491300635 @default.
- W3167014763 cites W1722318740 @default.
- W3167014763 cites W1731081199 @default.
- W3167014763 cites W1983320747 @default.
- W3167014763 cites W2034368206 @default.
- W3167014763 cites W2102605133 @default.
- W3167014763 cites W2104094955 @default.
- W3167014763 cites W2108598243 @default.
- W3167014763 cites W2111355007 @default.
- W3167014763 cites W2122837498 @default.
- W3167014763 cites W2136504847 @default.
- W3167014763 cites W2138776269 @default.
- W3167014763 cites W2144513243 @default.
- W3167014763 cites W2145494108 @default.
- W3167014763 cites W2154455818 @default.
- W3167014763 cites W2156557681 @default.
- W3167014763 cites W2159291411 @default.
- W3167014763 cites W2165698076 @default.
- W3167014763 cites W2194775991 @default.
- W3167014763 cites W2279034837 @default.
- W3167014763 cites W2463241543 @default.
- W3167014763 cites W2584009249 @default.
- W3167014763 cites W2592691248 @default.
- W3167014763 cites W2627183927 @default.
- W3167014763 cites W2765407302 @default.
- W3167014763 cites W2766897166 @default.
- W3167014763 cites W2786559811 @default.
- W3167014763 cites W2786808285 @default.
- W3167014763 cites W2795155917 @default.
- W3167014763 cites W2803297029 @default.
- W3167014763 cites W2895281799 @default.
- W3167014763 cites W2897536120 @default.
- W3167014763 cites W2912280829 @default.
- W3167014763 cites W2946812986 @default.
- W3167014763 cites W2951357534 @default.
- W3167014763 cites W2962687275 @default.
- W3167014763 cites W2962947361 @default.
- W3167014763 cites W2962986791 @default.
- W3167014763 cites W2963094258 @default.
- W3167014763 cites W2963449430 @default.
- W3167014763 cites W2963532621 @default.
- W3167014763 cites W2963956526 @default.
- W3167014763 cites W2964159205 @default.
- W3167014763 cites W2978426779 @default.
- W3167014763 cites W2979920800 @default.
- W3167014763 cites W2981720610 @default.
- W3167014763 cites W2982204955 @default.
- W3167014763 cites W2984353870 @default.
- W3167014763 cites W2985406498 @default.
- W3167014763 cites W2996501936 @default.
- W3167014763 cites W3001197829 @default.
- W3167014763 cites W3035519852 @default.
- W3167014763 cites W3039883906 @default.
- W3167014763 cites W3094146654 @default.
- W3167014763 cites W3095253761 @default.
- W3167014763 cites W3102631365 @default.
- W3167014763 cites W3102758664 @default.
- W3167014763 cites W3106031848 @default.
- W3167014763 cites W3109093849 @default.
- W3167014763 cites W2530816535 @default.
- W3167014763 hasPublicationYear "2021" @default.
- W3167014763 type Work @default.
- W3167014763 sameAs 3167014763 @default.
- W3167014763 citedByCount "1" @default.
- W3167014763 countsByYear W31670147632021 @default.
- W3167014763 crossrefType "posted-content" @default.
- W3167014763 hasAuthorship W3167014763A5016991275 @default.
- W3167014763 hasAuthorship W3167014763A5040092039 @default.
- W3167014763 hasAuthorship W3167014763A5065912071 @default.
- W3167014763 hasAuthorship W3167014763A5065964089 @default.
- W3167014763 hasAuthorship W3167014763A5087859582 @default.
- W3167014763 hasAuthorship W3167014763A5091460874 @default.
- W3167014763 hasConcept C119857082 @default.
- W3167014763 hasConcept C120665830 @default.
- W3167014763 hasConcept C121332964 @default.
- W3167014763 hasConcept C13280743 @default.
- W3167014763 hasConcept C134306372 @default.
- W3167014763 hasConcept C139807058 @default.
- W3167014763 hasConcept C154945302 @default.
- W3167014763 hasConcept C162324750 @default.
- W3167014763 hasConcept C185798385 @default.
- W3167014763 hasConcept C187736073 @default.
- W3167014763 hasConcept C205649164 @default.
- W3167014763 hasConcept C2776434776 @default.
- W3167014763 hasConcept C2780451532 @default.
- W3167014763 hasConcept C33923547 @default.
- W3167014763 hasConcept C36503486 @default.
- W3167014763 hasConcept C41008148 @default.
- W3167014763 hasConcept C95623464 @default.