Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092552955> ?p ?o ?g. }
- W3092552955 endingPage "4878" @default.
- W3092552955 startingPage "4864" @default.
- W3092552955 abstract "In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as domain adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good DA algorithms for these models. Herein we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several data sets, also outperforming other state-of-the-art DA algorithms." @default.
- W3092552955 created "2020-10-15" @default.
- W3092552955 creator A5020686179 @default.
- W3092552955 creator A5085151278 @default.
- W3092552955 creator A5086465725 @default.
- W3092552955 date "2021-11-01" @default.
- W3092552955 modified "2023-09-30" @default.
- W3092552955 title "Incremental Unsupervised Domain-Adversarial Training of Neural Networks" @default.
- W3092552955 cites W16455933 @default.
- W3092552955 cites W1722318740 @default.
- W3092552955 cites W183625566 @default.
- W3092552955 cites W1934241014 @default.
- W3092552955 cites W1970942930 @default.
- W3092552955 cites W2067713319 @default.
- W3092552955 cites W2104068492 @default.
- W3092552955 cites W2104094955 @default.
- W3092552955 cites W2106401878 @default.
- W3092552955 cites W2108069432 @default.
- W3092552955 cites W2108598243 @default.
- W3092552955 cites W2110158442 @default.
- W3092552955 cites W2112796928 @default.
- W3092552955 cites W2163345210 @default.
- W3092552955 cites W2183341477 @default.
- W3092552955 cites W2194775991 @default.
- W3092552955 cites W2478454054 @default.
- W3092552955 cites W2584009249 @default.
- W3092552955 cites W2593768305 @default.
- W3092552955 cites W2605488490 @default.
- W3092552955 cites W2744915377 @default.
- W3092552955 cites W2786808285 @default.
- W3092552955 cites W2895281799 @default.
- W3092552955 cites W2919115771 @default.
- W3092552955 cites W2962823940 @default.
- W3092552955 cites W2963187488 @default.
- W3092552955 cites W2964288524 @default.
- W3092552955 cites W2979509742 @default.
- W3092552955 cites W2981630749 @default.
- W3092552955 cites W2985406498 @default.
- W3092552955 cites W2986381065 @default.
- W3092552955 cites W4233762729 @default.
- W3092552955 doi "https://doi.org/10.1109/tnnls.2020.3025954" @default.
- W3092552955 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33027004" @default.
- W3092552955 hasPublicationYear "2021" @default.
- W3092552955 type Work @default.
- W3092552955 sameAs 3092552955 @default.
- W3092552955 citedByCount "20" @default.
- W3092552955 countsByYear W30925529552021 @default.
- W3092552955 countsByYear W30925529552022 @default.
- W3092552955 countsByYear W30925529552023 @default.
- W3092552955 crossrefType "journal-article" @default.
- W3092552955 hasAuthorship W3092552955A5020686179 @default.
- W3092552955 hasAuthorship W3092552955A5085151278 @default.
- W3092552955 hasAuthorship W3092552955A5086465725 @default.
- W3092552955 hasBestOaLocation W30925529552 @default.
- W3092552955 hasConcept C103278499 @default.
- W3092552955 hasConcept C111919701 @default.
- W3092552955 hasConcept C115961682 @default.
- W3092552955 hasConcept C119857082 @default.
- W3092552955 hasConcept C120665830 @default.
- W3092552955 hasConcept C121332964 @default.
- W3092552955 hasConcept C134306372 @default.
- W3092552955 hasConcept C139807058 @default.
- W3092552955 hasConcept C151730666 @default.
- W3092552955 hasConcept C153180895 @default.
- W3092552955 hasConcept C154945302 @default.
- W3092552955 hasConcept C169903167 @default.
- W3092552955 hasConcept C177264268 @default.
- W3092552955 hasConcept C199360897 @default.
- W3092552955 hasConcept C2779343474 @default.
- W3092552955 hasConcept C33923547 @default.
- W3092552955 hasConcept C36503486 @default.
- W3092552955 hasConcept C37736160 @default.
- W3092552955 hasConcept C41008148 @default.
- W3092552955 hasConcept C50644808 @default.
- W3092552955 hasConcept C86803240 @default.
- W3092552955 hasConcept C98045186 @default.
- W3092552955 hasConceptScore W3092552955C103278499 @default.
- W3092552955 hasConceptScore W3092552955C111919701 @default.
- W3092552955 hasConceptScore W3092552955C115961682 @default.
- W3092552955 hasConceptScore W3092552955C119857082 @default.
- W3092552955 hasConceptScore W3092552955C120665830 @default.
- W3092552955 hasConceptScore W3092552955C121332964 @default.
- W3092552955 hasConceptScore W3092552955C134306372 @default.
- W3092552955 hasConceptScore W3092552955C139807058 @default.
- W3092552955 hasConceptScore W3092552955C151730666 @default.
- W3092552955 hasConceptScore W3092552955C153180895 @default.
- W3092552955 hasConceptScore W3092552955C154945302 @default.
- W3092552955 hasConceptScore W3092552955C169903167 @default.
- W3092552955 hasConceptScore W3092552955C177264268 @default.
- W3092552955 hasConceptScore W3092552955C199360897 @default.
- W3092552955 hasConceptScore W3092552955C2779343474 @default.
- W3092552955 hasConceptScore W3092552955C33923547 @default.
- W3092552955 hasConceptScore W3092552955C36503486 @default.
- W3092552955 hasConceptScore W3092552955C37736160 @default.
- W3092552955 hasConceptScore W3092552955C41008148 @default.
- W3092552955 hasConceptScore W3092552955C50644808 @default.
- W3092552955 hasConceptScore W3092552955C86803240 @default.
- W3092552955 hasConceptScore W3092552955C98045186 @default.