FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322096612> ?p ?o ?g. }

• W4322096612 endingPage "356" @default.
• W4322096612 startingPage "338" @default.
• W4322096612 abstract "Unsupervised Domain Adaptation (UDA) aims to leverage the labeled source data and unlabeled target data to generalize better in the target domain. UDA methods utilize better domain alignment or carefully-designed regularizations to increase the discriminability of target features. However, most methods focus on directly increasing the distance between cluster centers of target features, i.e., enlarging inter-class variance, which intuitively increases the discriminability of target features and is easy to implement. However, due to intra-class variance optimization being under-explored, there are still some samples of the same class are prone to be classified into several classes. To handle this problem, we aim to equip UDA methods with the high smoothness constraint. We first define the model’s smoothness as the predictions similarity within each class, and propose a simple yet effective technique LeCo (impLicit smoothness Constraint) to promote the smoothness. We construct the weak and strong “views” of each target sample and enforce the model predictions of these two views to be consistent. Besides, a new uncertainty measure named Instance Class Confusion conditions the consistency is proposed to guarantee the transferability. LeCo implicitly reduces the model sensitivity to perturbations for target samples and guarantees smaller intra-class variance. Extensive experiments show that the proposed technique improves various baseline approaches by a large margin, and helps yield comparable results to the state-of-the-arts on four public datasets. Our codes are publicly available at https://github.com/Wang-Xiaodong1899/LeCo_UDA ." @default.
• W4322096612 created "2023-02-26" @default.
• W4322096612 creator A5001393670 @default.
• W4322096612 creator A5034112897 @default.
• W4322096612 creator A5040205022 @default.
• W4322096612 creator A5056480326 @default.
• W4322096612 creator A5088688674 @default.
• W4322096612 date "2023-01-01" @default.
• W4322096612 modified "2023-10-01" @default.
• W4322096612 title "Revisiting Unsupervised Domain Adaptation Models: A Smoothness Perspective" @default.
• W4322096612 cites W1722318740 @default.
• W4322096612 cites W1934241014 @default.
• W4322096612 cites W2034368206 @default.
• W4322096612 cites W2104094955 @default.
• W4322096612 cites W2164943005 @default.
• W4322096612 cites W2194775991 @default.
• W4322096612 cites W2593768305 @default.
• W4322096612 cites W2627183927 @default.
• W4322096612 cites W2767179670 @default.
• W4322096612 cites W2895771689 @default.
• W4322096612 cites W2904549000 @default.
• W4322096612 cites W2937614441 @default.
• W4322096612 cites W2962687275 @default.
• W4322096612 cites W2963532621 @default.
• W4322096612 cites W2981720610 @default.
• W4322096612 cites W2982204955 @default.
• W4322096612 cites W2986381065 @default.
• W4322096612 cites W3034218934 @default.
• W4322096612 cites W3034247804 @default.
• W4322096612 cites W3035519852 @default.
• W4322096612 cites W3035524453 @default.
• W4322096612 cites W3035576098 @default.
• W4322096612 cites W3035682985 @default.
• W4322096612 cites W3109093849 @default.
• W4322096612 cites W3110080985 @default.
• W4322096612 cites W3135384301 @default.
• W4322096612 cites W3159481202 @default.
• W4322096612 cites W3175370657 @default.
• W4322096612 cites W3176602994 @default.
• W4322096612 cites W3177316921 @default.
• W4322096612 cites W3206154535 @default.
• W4322096612 cites W3209458476 @default.
• W4322096612 cites W4286776233 @default.
• W4322096612 cites W4295046474 @default.
• W4322096612 cites W4313156423 @default.
• W4322096612 doi "https://doi.org/10.1007/978-3-031-26351-4_21" @default.
• W4322096612 hasPublicationYear "2023" @default.
• W4322096612 type Work @default.
• W4322096612 citedByCount "0" @default.
• W4322096612 crossrefType "book-chapter" @default.
• W4322096612 hasAuthorship W4322096612A5001393670 @default.
• W4322096612 hasAuthorship W4322096612A5034112897 @default.
• W4322096612 hasAuthorship W4322096612A5040205022 @default.
• W4322096612 hasAuthorship W4322096612A5056480326 @default.
• W4322096612 hasAuthorship W4322096612A5088688674 @default.
• W4322096612 hasConcept C102634674 @default.
• W4322096612 hasConcept C11413529 @default.
• W4322096612 hasConcept C119857082 @default.
• W4322096612 hasConcept C120665830 @default.
• W4322096612 hasConcept C121332964 @default.
• W4322096612 hasConcept C121955636 @default.
• W4322096612 hasConcept C124101348 @default.
• W4322096612 hasConcept C12713177 @default.
• W4322096612 hasConcept C134306372 @default.
• W4322096612 hasConcept C144133560 @default.
• W4322096612 hasConcept C153083717 @default.
• W4322096612 hasConcept C153180895 @default.
• W4322096612 hasConcept C154945302 @default.
• W4322096612 hasConcept C192209626 @default.
• W4322096612 hasConcept C196083921 @default.
• W4322096612 hasConcept C2524010 @default.
• W4322096612 hasConcept C2776036281 @default.
• W4322096612 hasConcept C2776434776 @default.
• W4322096612 hasConcept C2777212361 @default.
• W4322096612 hasConcept C33923547 @default.
• W4322096612 hasConcept C41008148 @default.
• W4322096612 hasConcept C774472 @default.
• W4322096612 hasConcept C95623464 @default.
• W4322096612 hasConceptScore W4322096612C102634674 @default.
• W4322096612 hasConceptScore W4322096612C11413529 @default.
• W4322096612 hasConceptScore W4322096612C119857082 @default.
• W4322096612 hasConceptScore W4322096612C120665830 @default.
• W4322096612 hasConceptScore W4322096612C121332964 @default.
• W4322096612 hasConceptScore W4322096612C121955636 @default.
• W4322096612 hasConceptScore W4322096612C124101348 @default.
• W4322096612 hasConceptScore W4322096612C12713177 @default.
• W4322096612 hasConceptScore W4322096612C134306372 @default.
• W4322096612 hasConceptScore W4322096612C144133560 @default.
• W4322096612 hasConceptScore W4322096612C153083717 @default.
• W4322096612 hasConceptScore W4322096612C153180895 @default.
• W4322096612 hasConceptScore W4322096612C154945302 @default.
• W4322096612 hasConceptScore W4322096612C192209626 @default.
• W4322096612 hasConceptScore W4322096612C196083921 @default.
• W4322096612 hasConceptScore W4322096612C2524010 @default.
• W4322096612 hasConceptScore W4322096612C2776036281 @default.
• W4322096612 hasConceptScore W4322096612C2776434776 @default.
• W4322096612 hasConceptScore W4322096612C2777212361 @default.
• W4322096612 hasConceptScore W4322096612C33923547 @default.

• next