Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100126235> ?p ?o ?g. }
- W3100126235 endingPage "10046" @default.
- W3100126235 startingPage "10035" @default.
- W3100126235 abstract "Cross-domain scene classification identifies scene categories by learning knowledge from a labeled data set (source domain) to an unlabeled data set (target domain), where the source data and the target data are sampled from different distributions. A lot of domain adaptation methods are used to reduce the distribution shift across domains, and most existing methods assume that the source domain shares the same categories with the target domain. It is usually hard to find a source domain that covers all categories in the target domain. Some works exploit multiple incomplete source domains to cover the target domain. However, in such setting, the categories of each source domain are a subset of the target-domain categories, and the target domain contains “unknown” categories for each source domain. The existence of unknown categories results in the conventional domain adaptation unsuitable. Known and unknown categories should be treated separately. Therefore, a separation mechanism is proposed to separate the known and unknown categories in this article. First, multiple-source classifiers trained on the multiple source domains are used to coarsely separate the known/unknown categories in the target domain. The target images with high similarities to source images are selected as known categories, and the target images with low similarities are selected as unknown categories. Then, a binary classifier trained using the selected images is used to finely separate all target-domain images. Finally, only the known categories are implemented in the cross-domain alignment and classification. The target images get labels by integrating the hypotheses of multiple-source classifiers on the known categories. Experiments are conducted on three cross-domain data sets to demonstrate the effectiveness of the proposed method." @default.
- W3100126235 created "2020-11-23" @default.
- W3100126235 creator A5007883693 @default.
- W3100126235 creator A5018824735 @default.
- W3100126235 creator A5065068394 @default.
- W3100126235 date "2021-12-01" @default.
- W3100126235 modified "2023-10-11" @default.
- W3100126235 title "Cross-Domain Scene Classification by Integrating Multiple Incomplete Sources" @default.
- W3100126235 cites W1980038761 @default.
- W3100126235 cites W2108598243 @default.
- W3100126235 cites W2115403315 @default.
- W3100126235 cites W2119880843 @default.
- W3100126235 cites W2526075485 @default.
- W3100126235 cites W2548624619 @default.
- W3100126235 cites W2551868040 @default.
- W3100126235 cites W2567257788 @default.
- W3100126235 cites W2593768305 @default.
- W3100126235 cites W2610614780 @default.
- W3100126235 cites W2614424296 @default.
- W3100126235 cites W2626107033 @default.
- W3100126235 cites W2766742564 @default.
- W3100126235 cites W2793797551 @default.
- W3100126235 cites W2800903797 @default.
- W3100126235 cites W2804188964 @default.
- W3100126235 cites W2804196292 @default.
- W3100126235 cites W2899885135 @default.
- W3100126235 cites W2901389242 @default.
- W3100126235 cites W2903882179 @default.
- W3100126235 cites W2909431441 @default.
- W3100126235 cites W2911305027 @default.
- W3100126235 cites W2914204846 @default.
- W3100126235 cites W2919206487 @default.
- W3100126235 cites W2948429981 @default.
- W3100126235 cites W2963506806 @default.
- W3100126235 cites W2964989774 @default.
- W3100126235 cites W2989738275 @default.
- W3100126235 cites W2991286101 @default.
- W3100126235 cites W2996590196 @default.
- W3100126235 cites W2997195386 @default.
- W3100126235 cites W3000175441 @default.
- W3100126235 cites W3004827100 @default.
- W3100126235 cites W3016406224 @default.
- W3100126235 cites W3103856189 @default.
- W3100126235 cites W3105577662 @default.
- W3100126235 cites W4285752776 @default.
- W3100126235 doi "https://doi.org/10.1109/tgrs.2020.3034344" @default.
- W3100126235 hasPublicationYear "2021" @default.
- W3100126235 type Work @default.
- W3100126235 sameAs 3100126235 @default.
- W3100126235 citedByCount "9" @default.
- W3100126235 countsByYear W31001262352021 @default.
- W3100126235 countsByYear W31001262352022 @default.
- W3100126235 crossrefType "journal-article" @default.
- W3100126235 hasAuthorship W3100126235A5007883693 @default.
- W3100126235 hasAuthorship W3100126235A5018824735 @default.
- W3100126235 hasAuthorship W3100126235A5065068394 @default.
- W3100126235 hasConcept C134306372 @default.
- W3100126235 hasConcept C153180895 @default.
- W3100126235 hasConcept C154945302 @default.
- W3100126235 hasConcept C165696696 @default.
- W3100126235 hasConcept C177264268 @default.
- W3100126235 hasConcept C199360897 @default.
- W3100126235 hasConcept C2776145971 @default.
- W3100126235 hasConcept C2776434776 @default.
- W3100126235 hasConcept C33923547 @default.
- W3100126235 hasConcept C36503486 @default.
- W3100126235 hasConcept C38652104 @default.
- W3100126235 hasConcept C41008148 @default.
- W3100126235 hasConcept C95623464 @default.
- W3100126235 hasConceptScore W3100126235C134306372 @default.
- W3100126235 hasConceptScore W3100126235C153180895 @default.
- W3100126235 hasConceptScore W3100126235C154945302 @default.
- W3100126235 hasConceptScore W3100126235C165696696 @default.
- W3100126235 hasConceptScore W3100126235C177264268 @default.
- W3100126235 hasConceptScore W3100126235C199360897 @default.
- W3100126235 hasConceptScore W3100126235C2776145971 @default.
- W3100126235 hasConceptScore W3100126235C2776434776 @default.
- W3100126235 hasConceptScore W3100126235C33923547 @default.
- W3100126235 hasConceptScore W3100126235C36503486 @default.
- W3100126235 hasConceptScore W3100126235C38652104 @default.
- W3100126235 hasConceptScore W3100126235C41008148 @default.
- W3100126235 hasConceptScore W3100126235C95623464 @default.
- W3100126235 hasFunder F4320321001 @default.
- W3100126235 hasFunder F4320321133 @default.
- W3100126235 hasFunder F4320336125 @default.
- W3100126235 hasFunder F4320336567 @default.
- W3100126235 hasIssue "12" @default.
- W3100126235 hasLocation W31001262351 @default.
- W3100126235 hasOpenAccess W3100126235 @default.
- W3100126235 hasPrimaryLocation W31001262351 @default.
- W3100126235 hasRelatedWork W1594039573 @default.
- W3100126235 hasRelatedWork W2341113105 @default.
- W3100126235 hasRelatedWork W2563096758 @default.
- W3100126235 hasRelatedWork W3035557009 @default.
- W3100126235 hasRelatedWork W3046182208 @default.
- W3100126235 hasRelatedWork W3100126235 @default.
- W3100126235 hasRelatedWork W3132602785 @default.
- W3100126235 hasRelatedWork W3204418343 @default.