Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093343057> ?p ?o ?g. }
- W3093343057 abstract "Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-effective it is desirable to select a maximally-informative subset via active learning (AL). We study the problem of AL under a domain shift, called Active Domain Adaptation (Active DA). We empirically demonstrate how existing AL approaches based solely on model uncertainty or diversity sampling are suboptimal for Active DA. Our algorithm, Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings (ADA-CLUE), i) identifies target instances for labeling that are both uncertain under the model and diverse in feature space, and ii) leverages the available source and target data for adaptation by optimizing a semi-supervised adversarial entropy loss that is complementary to our active sampling objective. On standard image classification-based domain adaptation benchmarks, ADA-CLUE consistently outperforms competing active adaptation, active learning, and domain adaptation methods across domain shifts of varying severity." @default.
- W3093343057 created "2020-10-22" @default.
- W3093343057 creator A5038068459 @default.
- W3093343057 creator A5063467976 @default.
- W3093343057 creator A5075906727 @default.
- W3093343057 creator A5077407640 @default.
- W3093343057 date "2020-10-16" @default.
- W3093343057 modified "2023-09-23" @default.
- W3093343057 title "Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings" @default.
- W3093343057 cites W1514940655 @default.
- W3093343057 cites W1522301498 @default.
- W3093343057 cites W1565327149 @default.
- W3093343057 cites W1722318740 @default.
- W3093343057 cites W1731081199 @default.
- W3093343057 cites W1787040602 @default.
- W3093343057 cites W1845402413 @default.
- W3093343057 cites W1934241014 @default.
- W3093343057 cites W1977556410 @default.
- W3093343057 cites W2011674654 @default.
- W3093343057 cites W2031342017 @default.
- W3093343057 cites W2034368206 @default.
- W3093343057 cites W2073459066 @default.
- W3093343057 cites W2096943734 @default.
- W3093343057 cites W2101234009 @default.
- W3093343057 cites W2112796928 @default.
- W3093343057 cites W2117539524 @default.
- W3093343057 cites W2120887445 @default.
- W3093343057 cites W2121010533 @default.
- W3093343057 cites W2140679654 @default.
- W3093343057 cites W2151023586 @default.
- W3093343057 cites W2157639208 @default.
- W3093343057 cites W2159291411 @default.
- W3093343057 cites W2161033259 @default.
- W3093343057 cites W2171852577 @default.
- W3093343057 cites W2187089797 @default.
- W3093343057 cites W2194775991 @default.
- W3093343057 cites W2293363371 @default.
- W3093343057 cites W2335728318 @default.
- W3093343057 cites W2426031434 @default.
- W3093343057 cites W2532189199 @default.
- W3093343057 cites W2593768305 @default.
- W3093343057 cites W2597787948 @default.
- W3093343057 cites W2767623047 @default.
- W3093343057 cites W2788686132 @default.
- W3093343057 cites W2903158431 @default.
- W3093343057 cites W2910982074 @default.
- W3093343057 cites W2911333381 @default.
- W3093343057 cites W2962808524 @default.
- W3093343057 cites W2962970380 @default.
- W3093343057 cites W2963741406 @default.
- W3093343057 cites W2963826681 @default.
- W3093343057 cites W2963902936 @default.
- W3093343057 cites W2970693987 @default.
- W3093343057 cites W2970859221 @default.
- W3093343057 cites W2970971581 @default.
- W3093343057 cites W2981720610 @default.
- W3093343057 cites W2986381065 @default.
- W3093343057 cites W2986514296 @default.
- W3093343057 cites W2995188922 @default.
- W3093343057 cites W2995700071 @default.
- W3093343057 cites W3010360081 @default.
- W3093343057 cites W603830301 @default.
- W3093343057 cites W77777798 @default.
- W3093343057 cites W2735531870 @default.
- W3093343057 cites W2998213596 @default.
- W3093343057 hasPublicationYear "2020" @default.
- W3093343057 type Work @default.
- W3093343057 sameAs 3093343057 @default.
- W3093343057 citedByCount "0" @default.
- W3093343057 crossrefType "posted-content" @default.
- W3093343057 hasAuthorship W3093343057A5038068459 @default.
- W3093343057 hasAuthorship W3093343057A5063467976 @default.
- W3093343057 hasAuthorship W3093343057A5075906727 @default.
- W3093343057 hasAuthorship W3093343057A5077407640 @default.
- W3093343057 hasConcept C106301342 @default.
- W3093343057 hasConcept C119857082 @default.
- W3093343057 hasConcept C120665830 @default.
- W3093343057 hasConcept C121332964 @default.
- W3093343057 hasConcept C124101348 @default.
- W3093343057 hasConcept C134306372 @default.
- W3093343057 hasConcept C139807058 @default.
- W3093343057 hasConcept C153180895 @default.
- W3093343057 hasConcept C154945302 @default.
- W3093343057 hasConcept C2776434776 @default.
- W3093343057 hasConcept C33923547 @default.
- W3093343057 hasConcept C36503486 @default.
- W3093343057 hasConcept C37736160 @default.
- W3093343057 hasConcept C41008148 @default.
- W3093343057 hasConcept C62520636 @default.
- W3093343057 hasConcept C73555534 @default.
- W3093343057 hasConcept C77967617 @default.
- W3093343057 hasConcept C95623464 @default.
- W3093343057 hasConceptScore W3093343057C106301342 @default.
- W3093343057 hasConceptScore W3093343057C119857082 @default.
- W3093343057 hasConceptScore W3093343057C120665830 @default.
- W3093343057 hasConceptScore W3093343057C121332964 @default.
- W3093343057 hasConceptScore W3093343057C124101348 @default.
- W3093343057 hasConceptScore W3093343057C134306372 @default.
- W3093343057 hasConceptScore W3093343057C139807058 @default.
- W3093343057 hasConceptScore W3093343057C153180895 @default.