Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137663145> ?p ?o ?g. }
- W3137663145 abstract "Unsupervised domain adaptation (UDA) aims to improve the classification performance on an unlabeled target domain by leveraging information from a fully labeled source domain. Recent approaches explore domain-invariant and class-discriminant representations to tackle this task. These methods, however, ignore the interaction between domain alignment learning and class discrimination learning. As a result, the missing or inadequate tradeoff between domain alignment and class discrimination are prone to the problem of negative transfer. In this paper, we propose Dynamic Weighted Learning (DWL) to avoid the discriminability vanishing problem caused by excessive alignment learning and domain misalignment problem caused by excessive discriminant learning. Technically, DWL dynamically weights the learning losses of alignment and discriminability by introducing the degree of alignment and discriminability. Besides, the problem of sample imbalance across domains is first considered in our work, and we solve the problem by weighing the samples to guarantee information balance across domains. Extensive experiments demonstrate that DWL has an excellent performance in several benchmark datasets." @default.
- W3137663145 created "2021-03-29" @default.
- W3137663145 creator A5071798264 @default.
- W3137663145 creator A5083173164 @default.
- W3137663145 date "2021-03-22" @default.
- W3137663145 modified "2023-09-23" @default.
- W3137663145 title "Dynamic Weighted Learning for Unsupervised Domain Adaptation" @default.
- W3137663145 cites W1565327149 @default.
- W3137663145 cites W1722318740 @default.
- W3137663145 cites W1731081199 @default.
- W3137663145 cites W2096943734 @default.
- W3137663145 cites W2099471712 @default.
- W3137663145 cites W2104068492 @default.
- W3137663145 cites W2104094955 @default.
- W3137663145 cites W2107388088 @default.
- W3137663145 cites W2108598243 @default.
- W3137663145 cites W2112796928 @default.
- W3137663145 cites W2159291411 @default.
- W3137663145 cites W2194775991 @default.
- W3137663145 cites W2283717164 @default.
- W3137663145 cites W2335728318 @default.
- W3137663145 cites W2478454054 @default.
- W3137663145 cites W2511131004 @default.
- W3137663145 cites W2552765257 @default.
- W3137663145 cites W2593768305 @default.
- W3137663145 cites W2605488490 @default.
- W3137663145 cites W2751528152 @default.
- W3137663145 cites W2766897166 @default.
- W3137663145 cites W2795155917 @default.
- W3137663145 cites W2798328860 @default.
- W3137663145 cites W2798681837 @default.
- W3137663145 cites W2803106019 @default.
- W3137663145 cites W2803297029 @default.
- W3137663145 cites W2899011088 @default.
- W3137663145 cites W2945328857 @default.
- W3137663145 cites W2946812986 @default.
- W3137663145 cites W2962687275 @default.
- W3137663145 cites W2962808524 @default.
- W3137663145 cites W2963784072 @default.
- W3137663145 cites W2963826681 @default.
- W3137663145 cites W2964278684 @default.
- W3137663145 cites W2964288524 @default.
- W3137663145 cites W2978573218 @default.
- W3137663145 cites W2982204955 @default.
- W3137663145 cites W2991405316 @default.
- W3137663145 cites W2997310315 @default.
- W3137663145 cites W3010360081 @default.
- W3137663145 cites W3025988480 @default.
- W3137663145 cites W3035297522 @default.
- W3137663145 cites W3035456997 @default.
- W3137663145 doi "https://doi.org/10.48550/arxiv.2103.13814" @default.
- W3137663145 hasPublicationYear "2021" @default.
- W3137663145 type Work @default.
- W3137663145 sameAs 3137663145 @default.
- W3137663145 citedByCount "1" @default.
- W3137663145 countsByYear W31376631452021 @default.
- W3137663145 crossrefType "posted-content" @default.
- W3137663145 hasAuthorship W3137663145A5071798264 @default.
- W3137663145 hasAuthorship W3137663145A5083173164 @default.
- W3137663145 hasBestOaLocation W31376631451 @default.
- W3137663145 hasConcept C119857082 @default.
- W3137663145 hasConcept C120665830 @default.
- W3137663145 hasConcept C121332964 @default.
- W3137663145 hasConcept C13280743 @default.
- W3137663145 hasConcept C134306372 @default.
- W3137663145 hasConcept C139807058 @default.
- W3137663145 hasConcept C150899416 @default.
- W3137663145 hasConcept C153180895 @default.
- W3137663145 hasConcept C154945302 @default.
- W3137663145 hasConcept C185798385 @default.
- W3137663145 hasConcept C205649164 @default.
- W3137663145 hasConcept C2776434776 @default.
- W3137663145 hasConcept C2777212361 @default.
- W3137663145 hasConcept C33923547 @default.
- W3137663145 hasConcept C36503486 @default.
- W3137663145 hasConcept C41008148 @default.
- W3137663145 hasConcept C69738355 @default.
- W3137663145 hasConcept C78397625 @default.
- W3137663145 hasConcept C8038995 @default.
- W3137663145 hasConcept C95623464 @default.
- W3137663145 hasConceptScore W3137663145C119857082 @default.
- W3137663145 hasConceptScore W3137663145C120665830 @default.
- W3137663145 hasConceptScore W3137663145C121332964 @default.
- W3137663145 hasConceptScore W3137663145C13280743 @default.
- W3137663145 hasConceptScore W3137663145C134306372 @default.
- W3137663145 hasConceptScore W3137663145C139807058 @default.
- W3137663145 hasConceptScore W3137663145C150899416 @default.
- W3137663145 hasConceptScore W3137663145C153180895 @default.
- W3137663145 hasConceptScore W3137663145C154945302 @default.
- W3137663145 hasConceptScore W3137663145C185798385 @default.
- W3137663145 hasConceptScore W3137663145C205649164 @default.
- W3137663145 hasConceptScore W3137663145C2776434776 @default.
- W3137663145 hasConceptScore W3137663145C2777212361 @default.
- W3137663145 hasConceptScore W3137663145C33923547 @default.
- W3137663145 hasConceptScore W3137663145C36503486 @default.
- W3137663145 hasConceptScore W3137663145C41008148 @default.
- W3137663145 hasConceptScore W3137663145C69738355 @default.
- W3137663145 hasConceptScore W3137663145C78397625 @default.
- W3137663145 hasConceptScore W3137663145C8038995 @default.
- W3137663145 hasConceptScore W3137663145C95623464 @default.