Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313261037> ?p ?o ?g. }
- W4313261037 endingPage "99" @default.
- W4313261037 startingPage "99" @default.
- W4313261037 abstract "In recent years, computer vision tasks have increasingly used deep learning techniques. In some tasks, however, due to insufficient data, the model is not properly trained, leading to a decrease in generalizability. When trained on a dataset and tested on another similar dataset, the model predicts near-random results. This paper presents an unsupervised multi-source domain adaptation that improves transfer learning and increases generalizability. In the proposed method, a new module infers the source of the input data based on its extracted features. By making the features extractor compete against this objective, the learned feature representation generalizes better across the sources. As a result, representations similar to those from different sources are learned. That is, the extracted representation is generic and independent of any particular domain. In the training stage, a non-Euclidean triplet loss function is also utilized. Similar representations for samples belonging to the same class can be learned more effectively using the proposed loss function. We demonstrate how the developed framework may be applied to enhance accuracy and outperform the outcomes of already effective transfer learning methodologies. We demonstrate how the proposed strategy performs particularly well when dealing with various dataset domains or when there are insufficient data." @default.
- W4313261037 created "2023-01-06" @default.
- W4313261037 creator A5034670191 @default.
- W4313261037 creator A5056445813 @default.
- W4313261037 creator A5089205977 @default.
- W4313261037 date "2022-12-26" @default.
- W4313261037 modified "2023-10-18" @default.
- W4313261037 title "Unsupervised Domain Adaptation for Image Classification Using Non-Euclidean Triplet Loss" @default.
- W4313261037 cites W1968723779 @default.
- W4313261037 cites W2005096862 @default.
- W4313261037 cites W2047568922 @default.
- W4313261037 cites W2084220915 @default.
- W4313261037 cites W2112796928 @default.
- W4313261037 cites W2194775991 @default.
- W4313261037 cites W2557738935 @default.
- W4313261037 cites W2560476520 @default.
- W4313261037 cites W2565684601 @default.
- W4313261037 cites W2580480204 @default.
- W4313261037 cites W2584009249 @default.
- W4313261037 cites W2605488490 @default.
- W4313261037 cites W2744915377 @default.
- W4313261037 cites W2915678294 @default.
- W4313261037 cites W2948689807 @default.
- W4313261037 cites W2955547856 @default.
- W4313261037 cites W2962687275 @default.
- W4313261037 cites W2963956348 @default.
- W4313261037 cites W2963993484 @default.
- W4313261037 cites W2980096013 @default.
- W4313261037 cites W3026850250 @default.
- W4313261037 cites W3035297522 @default.
- W4313261037 cites W3035456997 @default.
- W4313261037 cites W3045686297 @default.
- W4313261037 cites W3085306326 @default.
- W4313261037 cites W3086039674 @default.
- W4313261037 cites W3093282986 @default.
- W4313261037 cites W3099206234 @default.
- W4313261037 cites W3105081694 @default.
- W4313261037 cites W3172118802 @default.
- W4313261037 cites W3181434681 @default.
- W4313261037 cites W3195711320 @default.
- W4313261037 cites W3202947444 @default.
- W4313261037 cites W3206188013 @default.
- W4313261037 cites W3208697304 @default.
- W4313261037 cites W3210407768 @default.
- W4313261037 cites W3210628769 @default.
- W4313261037 cites W4205341929 @default.
- W4313261037 cites W4210992544 @default.
- W4313261037 cites W4225648146 @default.
- W4313261037 cites W4283811563 @default.
- W4313261037 cites W4285821176 @default.
- W4313261037 cites W4293912903 @default.
- W4313261037 doi "https://doi.org/10.3390/electronics12010099" @default.
- W4313261037 hasPublicationYear "2022" @default.
- W4313261037 type Work @default.
- W4313261037 citedByCount "0" @default.
- W4313261037 crossrefType "journal-article" @default.
- W4313261037 hasAuthorship W4313261037A5034670191 @default.
- W4313261037 hasAuthorship W4313261037A5056445813 @default.
- W4313261037 hasAuthorship W4313261037A5089205977 @default.
- W4313261037 hasBestOaLocation W43132610371 @default.
- W4313261037 hasConcept C105795698 @default.
- W4313261037 hasConcept C119857082 @default.
- W4313261037 hasConcept C120174047 @default.
- W4313261037 hasConcept C120665830 @default.
- W4313261037 hasConcept C121332964 @default.
- W4313261037 hasConcept C124101348 @default.
- W4313261037 hasConcept C134306372 @default.
- W4313261037 hasConcept C138885662 @default.
- W4313261037 hasConcept C139807058 @default.
- W4313261037 hasConcept C14036430 @default.
- W4313261037 hasConcept C150899416 @default.
- W4313261037 hasConcept C153180895 @default.
- W4313261037 hasConcept C154945302 @default.
- W4313261037 hasConcept C17744445 @default.
- W4313261037 hasConcept C199539241 @default.
- W4313261037 hasConcept C27158222 @default.
- W4313261037 hasConcept C2776359362 @default.
- W4313261037 hasConcept C2776401178 @default.
- W4313261037 hasConcept C2776434776 @default.
- W4313261037 hasConcept C2777212361 @default.
- W4313261037 hasConcept C33923547 @default.
- W4313261037 hasConcept C36503486 @default.
- W4313261037 hasConcept C41008148 @default.
- W4313261037 hasConcept C41895202 @default.
- W4313261037 hasConcept C59404180 @default.
- W4313261037 hasConcept C78458016 @default.
- W4313261037 hasConcept C86803240 @default.
- W4313261037 hasConcept C94625758 @default.
- W4313261037 hasConcept C95623464 @default.
- W4313261037 hasConceptScore W4313261037C105795698 @default.
- W4313261037 hasConceptScore W4313261037C119857082 @default.
- W4313261037 hasConceptScore W4313261037C120174047 @default.
- W4313261037 hasConceptScore W4313261037C120665830 @default.
- W4313261037 hasConceptScore W4313261037C121332964 @default.
- W4313261037 hasConceptScore W4313261037C124101348 @default.
- W4313261037 hasConceptScore W4313261037C134306372 @default.
- W4313261037 hasConceptScore W4313261037C138885662 @default.
- W4313261037 hasConceptScore W4313261037C139807058 @default.