Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386597308> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4386597308 abstract "Utilizing deep neural network for Domain Adaptation (DA) has made great progress on learning knowledge from source domain to solve tasks in other relevant target domains. However, conventional DA methods have several restrictions: first, the category set from the source and target domain should be identical; second, during the training process data from different domains are fed into the network simultaneously, which may not be practical in real-world applications. Consequently, we aim at tackling the Source Free Open Set Domain Adaptation scenario: source and target data cannot meet with each other and the target domain contains exclusive unknown classes. Specifically, we propose a method enhancing the unknown class identification ability by synthesizing unknown class data: a feature modifier with multiple Gated Recurrent Units (GRU) is designed to learn and modify key features from the input data in order that the modified data ’looks like’ the real unknown class class data. Both real and synthesis data are used to train the classifier such that it can identify each class correctly. We evaluate our method in multiple benchmarks and the proposed framework outperforms other methods in comparison." @default.
- W4386597308 created "2023-09-12" @default.
- W4386597308 creator A5014196059 @default.
- W4386597308 creator A5026657865 @default.
- W4386597308 creator A5070982537 @default.
- W4386597308 date "2023-10-08" @default.
- W4386597308 modified "2023-09-30" @default.
- W4386597308 title "Unknown Class Feature Transformation for Open Set Domain Adaptation Without Source Data" @default.
- W4386597308 cites W1032927584 @default.
- W4386597308 cites W2194775991 @default.
- W4386597308 cites W2627183927 @default.
- W4386597308 cites W2779610669 @default.
- W4386597308 cites W2798593490 @default.
- W4386597308 cites W2939645724 @default.
- W4386597308 cites W2948069880 @default.
- W4386597308 cites W2948429981 @default.
- W4386597308 cites W2963149653 @default.
- W4386597308 cites W3010381534 @default.
- W4386597308 cites W3118707261 @default.
- W4386597308 cites W3169002235 @default.
- W4386597308 cites W3175308890 @default.
- W4386597308 cites W3177151237 @default.
- W4386597308 doi "https://doi.org/10.1109/icip49359.2023.10222226" @default.
- W4386597308 hasPublicationYear "2023" @default.
- W4386597308 type Work @default.
- W4386597308 citedByCount "0" @default.
- W4386597308 crossrefType "proceedings-article" @default.
- W4386597308 hasAuthorship W4386597308A5014196059 @default.
- W4386597308 hasAuthorship W4386597308A5026657865 @default.
- W4386597308 hasAuthorship W4386597308A5070982537 @default.
- W4386597308 hasBestOaLocation W43865973081 @default.
- W4386597308 hasConcept C118615104 @default.
- W4386597308 hasConcept C119857082 @default.
- W4386597308 hasConcept C120665830 @default.
- W4386597308 hasConcept C121332964 @default.
- W4386597308 hasConcept C124101348 @default.
- W4386597308 hasConcept C134306372 @default.
- W4386597308 hasConcept C139807058 @default.
- W4386597308 hasConcept C153180895 @default.
- W4386597308 hasConcept C154945302 @default.
- W4386597308 hasConcept C177264268 @default.
- W4386597308 hasConcept C199360897 @default.
- W4386597308 hasConcept C2776434776 @default.
- W4386597308 hasConcept C2777212361 @default.
- W4386597308 hasConcept C33923547 @default.
- W4386597308 hasConcept C36503486 @default.
- W4386597308 hasConcept C41008148 @default.
- W4386597308 hasConcept C42357961 @default.
- W4386597308 hasConcept C51632099 @default.
- W4386597308 hasConcept C95623464 @default.
- W4386597308 hasConceptScore W4386597308C118615104 @default.
- W4386597308 hasConceptScore W4386597308C119857082 @default.
- W4386597308 hasConceptScore W4386597308C120665830 @default.
- W4386597308 hasConceptScore W4386597308C121332964 @default.
- W4386597308 hasConceptScore W4386597308C124101348 @default.
- W4386597308 hasConceptScore W4386597308C134306372 @default.
- W4386597308 hasConceptScore W4386597308C139807058 @default.
- W4386597308 hasConceptScore W4386597308C153180895 @default.
- W4386597308 hasConceptScore W4386597308C154945302 @default.
- W4386597308 hasConceptScore W4386597308C177264268 @default.
- W4386597308 hasConceptScore W4386597308C199360897 @default.
- W4386597308 hasConceptScore W4386597308C2776434776 @default.
- W4386597308 hasConceptScore W4386597308C2777212361 @default.
- W4386597308 hasConceptScore W4386597308C33923547 @default.
- W4386597308 hasConceptScore W4386597308C36503486 @default.
- W4386597308 hasConceptScore W4386597308C41008148 @default.
- W4386597308 hasConceptScore W4386597308C42357961 @default.
- W4386597308 hasConceptScore W4386597308C51632099 @default.
- W4386597308 hasConceptScore W4386597308C95623464 @default.
- W4386597308 hasFunder F4320321001 @default.
- W4386597308 hasFunder F4320321921 @default.
- W4386597308 hasLocation W43865973081 @default.
- W4386597308 hasOpenAccess W4386597308 @default.
- W4386597308 hasPrimaryLocation W43865973081 @default.
- W4386597308 hasRelatedWork W2152148513 @default.
- W4386597308 hasRelatedWork W2341113105 @default.
- W4386597308 hasRelatedWork W2563096758 @default.
- W4386597308 hasRelatedWork W2779610669 @default.
- W4386597308 hasRelatedWork W4281397339 @default.
- W4386597308 hasRelatedWork W4285121299 @default.
- W4386597308 hasRelatedWork W4312910505 @default.
- W4386597308 hasRelatedWork W4376166954 @default.
- W4386597308 hasRelatedWork W4386053843 @default.
- W4386597308 hasRelatedWork W3158004940 @default.
- W4386597308 isParatext "false" @default.
- W4386597308 isRetracted "false" @default.
- W4386597308 workType "article" @default.