Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999746632> ?p ?o ?g. }
- W2999746632 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. Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here 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 set is then added to the source training set by considering the labels provided by the network as ground truth, and the process is repeated until all target samples are labelled. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms." @default.
- W2999746632 created "2020-01-23" @default.
- W2999746632 creator A5063350194 @default.
- W2999746632 creator A5085151278 @default.
- W2999746632 creator A5086465725 @default.
- W2999746632 date "2020-01-13" @default.
- W2999746632 modified "2023-09-27" @default.
- W2999746632 title "Incremental Unsupervised Domain-Adversarial Training of Neural Networks" @default.
- W2999746632 cites W16455933 @default.
- W2999746632 cites W1731081199 @default.
- W2999746632 cites W183625566 @default.
- W2999746632 cites W1934241014 @default.
- W2999746632 cites W1970942930 @default.
- W2999746632 cites W2067713319 @default.
- W2999746632 cites W2095705004 @default.
- W2999746632 cites W2104068492 @default.
- W2999746632 cites W2104094955 @default.
- W2999746632 cites W2108069432 @default.
- W2999746632 cites W2110158442 @default.
- W2999746632 cites W2112796928 @default.
- W2999746632 cites W2131953535 @default.
- W2999746632 cites W2163345210 @default.
- W2999746632 cites W2183341477 @default.
- W2999746632 cites W2187089797 @default.
- W2999746632 cites W2194775991 @default.
- W2999746632 cites W2335728318 @default.
- W2999746632 cites W2478454054 @default.
- W2999746632 cites W2511131004 @default.
- W2999746632 cites W2557283755 @default.
- W2999746632 cites W2584009249 @default.
- W2999746632 cites W2593768305 @default.
- W2999746632 cites W2744915377 @default.
- W2999746632 cites W2786808285 @default.
- W2999746632 cites W2919115771 @default.
- W2999746632 cites W2949667497 @default.
- W2999746632 cites W2962835968 @default.
- W2999746632 cites W2962970380 @default.
- W2999746632 cites W2963187488 @default.
- W2999746632 cites W2964288524 @default.
- W2999746632 cites W2979509742 @default.
- W2999746632 cites W2981630749 @default.
- W2999746632 cites W2986381065 @default.
- W2999746632 cites W385466589 @default.
- W2999746632 hasPublicationYear "2020" @default.
- W2999746632 type Work @default.
- W2999746632 sameAs 2999746632 @default.
- W2999746632 citedByCount "0" @default.
- W2999746632 crossrefType "posted-content" @default.
- W2999746632 hasAuthorship W2999746632A5063350194 @default.
- W2999746632 hasAuthorship W2999746632A5085151278 @default.
- W2999746632 hasAuthorship W2999746632A5086465725 @default.
- W2999746632 hasConcept C103278499 @default.
- W2999746632 hasConcept C111919701 @default.
- W2999746632 hasConcept C115961682 @default.
- W2999746632 hasConcept C119857082 @default.
- W2999746632 hasConcept C120665830 @default.
- W2999746632 hasConcept C121332964 @default.
- W2999746632 hasConcept C124101348 @default.
- W2999746632 hasConcept C134306372 @default.
- W2999746632 hasConcept C139807058 @default.
- W2999746632 hasConcept C151730666 @default.
- W2999746632 hasConcept C153180895 @default.
- W2999746632 hasConcept C154945302 @default.
- W2999746632 hasConcept C169903167 @default.
- W2999746632 hasConcept C177264268 @default.
- W2999746632 hasConcept C199360897 @default.
- W2999746632 hasConcept C2776434776 @default.
- W2999746632 hasConcept C2779343474 @default.
- W2999746632 hasConcept C33923547 @default.
- W2999746632 hasConcept C36503486 @default.
- W2999746632 hasConcept C37736160 @default.
- W2999746632 hasConcept C41008148 @default.
- W2999746632 hasConcept C50644808 @default.
- W2999746632 hasConcept C86803240 @default.
- W2999746632 hasConcept C95623464 @default.
- W2999746632 hasConcept C98045186 @default.
- W2999746632 hasConceptScore W2999746632C103278499 @default.
- W2999746632 hasConceptScore W2999746632C111919701 @default.
- W2999746632 hasConceptScore W2999746632C115961682 @default.
- W2999746632 hasConceptScore W2999746632C119857082 @default.
- W2999746632 hasConceptScore W2999746632C120665830 @default.
- W2999746632 hasConceptScore W2999746632C121332964 @default.
- W2999746632 hasConceptScore W2999746632C124101348 @default.
- W2999746632 hasConceptScore W2999746632C134306372 @default.
- W2999746632 hasConceptScore W2999746632C139807058 @default.
- W2999746632 hasConceptScore W2999746632C151730666 @default.
- W2999746632 hasConceptScore W2999746632C153180895 @default.
- W2999746632 hasConceptScore W2999746632C154945302 @default.
- W2999746632 hasConceptScore W2999746632C169903167 @default.
- W2999746632 hasConceptScore W2999746632C177264268 @default.
- W2999746632 hasConceptScore W2999746632C199360897 @default.
- W2999746632 hasConceptScore W2999746632C2776434776 @default.
- W2999746632 hasConceptScore W2999746632C2779343474 @default.
- W2999746632 hasConceptScore W2999746632C33923547 @default.
- W2999746632 hasConceptScore W2999746632C36503486 @default.
- W2999746632 hasConceptScore W2999746632C37736160 @default.
- W2999746632 hasConceptScore W2999746632C41008148 @default.
- W2999746632 hasConceptScore W2999746632C50644808 @default.
- W2999746632 hasConceptScore W2999746632C86803240 @default.
- W2999746632 hasConceptScore W2999746632C95623464 @default.