Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177316921> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3177316921 endingPage "8464" @default.
- W3177316921 startingPage "8455" @default.
- W3177316921 abstract "Unsupervised domain adaptation challenges the problem of transferring knowledge from a well-labelled source domain to an unlabelled target domain. Recently, adversarial learning with bi-classifier has been proven effective in pushing cross-domain distributions close. Prior approaches typically leverage the disagreement between bi-classifier to learn transferable representations, however, they often neglect the classifier determinacy in the target domain, which could result in a lack of feature discriminability. In this paper, we present a simple yet effective method, namely Bi-Classifier Determinacy Maximization (BCDM), to tackle this problem. Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability. To this end, the BCDM can generate discriminative representations by encouraging target predictive outputs to be consistent and determined, meanwhile, preserve the diversity of predictions in an adversarial manner. Furthermore, the properties of CDD as well as the theoretical guarantees of BCDM's generalization bound are both elaborated. Extensive experiments show that BCDM compares favorably against the existing state-of-the-art domain adaptation methods." @default.
- W3177316921 created "2021-07-05" @default.
- W3177316921 creator A5001817133 @default.
- W3177316921 creator A5009558549 @default.
- W3177316921 creator A5028293439 @default.
- W3177316921 creator A5034541026 @default.
- W3177316921 creator A5061084605 @default.
- W3177316921 creator A5086988988 @default.
- W3177316921 date "2021-05-18" @default.
- W3177316921 modified "2023-10-15" @default.
- W3177316921 title "Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation" @default.
- W3177316921 doi "https://doi.org/10.1609/aaai.v35i10.17027" @default.
- W3177316921 hasPublicationYear "2021" @default.
- W3177316921 type Work @default.
- W3177316921 sameAs 3177316921 @default.
- W3177316921 citedByCount "26" @default.
- W3177316921 countsByYear W31773169212021 @default.
- W3177316921 countsByYear W31773169212022 @default.
- W3177316921 countsByYear W31773169212023 @default.
- W3177316921 crossrefType "journal-article" @default.
- W3177316921 hasAuthorship W3177316921A5001817133 @default.
- W3177316921 hasAuthorship W3177316921A5009558549 @default.
- W3177316921 hasAuthorship W3177316921A5028293439 @default.
- W3177316921 hasAuthorship W3177316921A5034541026 @default.
- W3177316921 hasAuthorship W3177316921A5061084605 @default.
- W3177316921 hasAuthorship W3177316921A5086988988 @default.
- W3177316921 hasBestOaLocation W31773169211 @default.
- W3177316921 hasConcept C119857082 @default.
- W3177316921 hasConcept C126255220 @default.
- W3177316921 hasConcept C134306372 @default.
- W3177316921 hasConcept C153180895 @default.
- W3177316921 hasConcept C154945302 @default.
- W3177316921 hasConcept C2776330181 @default.
- W3177316921 hasConcept C33923547 @default.
- W3177316921 hasConcept C41008148 @default.
- W3177316921 hasConcept C52620605 @default.
- W3177316921 hasConcept C58468513 @default.
- W3177316921 hasConcept C95623464 @default.
- W3177316921 hasConcept C97931131 @default.
- W3177316921 hasConceptScore W3177316921C119857082 @default.
- W3177316921 hasConceptScore W3177316921C126255220 @default.
- W3177316921 hasConceptScore W3177316921C134306372 @default.
- W3177316921 hasConceptScore W3177316921C153180895 @default.
- W3177316921 hasConceptScore W3177316921C154945302 @default.
- W3177316921 hasConceptScore W3177316921C2776330181 @default.
- W3177316921 hasConceptScore W3177316921C33923547 @default.
- W3177316921 hasConceptScore W3177316921C41008148 @default.
- W3177316921 hasConceptScore W3177316921C52620605 @default.
- W3177316921 hasConceptScore W3177316921C58468513 @default.
- W3177316921 hasConceptScore W3177316921C95623464 @default.
- W3177316921 hasConceptScore W3177316921C97931131 @default.
- W3177316921 hasIssue "10" @default.
- W3177316921 hasLocation W31773169211 @default.
- W3177316921 hasLocation W31773169212 @default.
- W3177316921 hasLocation W31773169213 @default.
- W3177316921 hasOpenAccess W3177316921 @default.
- W3177316921 hasPrimaryLocation W31773169211 @default.
- W3177316921 hasRelatedWork W1775174800 @default.
- W3177316921 hasRelatedWork W1983827846 @default.
- W3177316921 hasRelatedWork W2009506202 @default.
- W3177316921 hasRelatedWork W2096969571 @default.
- W3177316921 hasRelatedWork W2112112609 @default.
- W3177316921 hasRelatedWork W2162083125 @default.
- W3177316921 hasRelatedWork W2800999593 @default.
- W3177316921 hasRelatedWork W2951122819 @default.
- W3177316921 hasRelatedWork W4288315282 @default.
- W3177316921 hasRelatedWork W47559851 @default.
- W3177316921 hasVolume "35" @default.
- W3177316921 isParatext "false" @default.
- W3177316921 isRetracted "false" @default.
- W3177316921 magId "3177316921" @default.
- W3177316921 workType "article" @default.