Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209860877> ?p ?o ?g. }
- W3209860877 abstract "To alleviate lower classification performance on rare classes in imbalanced datasets, a possible solution is to augment the underrepresented classes with synthetic samples. Domain adaptation can be incorporated in a classifier to decrease the domain discrepancy between real and synthetic samples. While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples. As a testbed, we use a camera trap animal dataset with a rare deer class, which is augmented with synthetic deer samples. We adapt existing domain adaptation methods to two new methods for the single rare class setting: DeerDANN, based on the Domain-Adversarial Neural Network (DANN), and DeerCORAL, based on deep correlation alignment (Deep CORAL) architectures. Experiments show that DeerDANN has the highest improvement in deer classification accuracy of 24.0% versus 22.4% improvement of DeerCORAL when compared to the baseline. Further, both methods require fewer than 10k synthetic samples, as used by the baseline, to achieve these higher accuracies. DeerCORAL requires the least number of synthetic samples (2k deer), followed by DeerDANN (8k deer)." @default.
- W3209860877 created "2021-11-08" @default.
- W3209860877 creator A5042244876 @default.
- W3209860877 creator A5052695749 @default.
- W3209860877 creator A5055165096 @default.
- W3209860877 creator A5077258803 @default.
- W3209860877 creator A5085480111 @default.
- W3209860877 date "2021-10-23" @default.
- W3209860877 modified "2023-09-27" @default.
- W3209860877 title "Domain Adaptation for Rare Classes Augmented with Synthetic Samples" @default.
- W3209860877 cites W1565327149 @default.
- W3209860877 cites W1987716715 @default.
- W3209860877 cites W2010132303 @default.
- W3209860877 cites W2034603029 @default.
- W3209860877 cites W2073246097 @default.
- W3209860877 cites W2108598243 @default.
- W3209860877 cites W2153062878 @default.
- W3209860877 cites W2165698076 @default.
- W3209860877 cites W2183341477 @default.
- W3209860877 cites W2187089797 @default.
- W3209860877 cites W2194775991 @default.
- W3209860877 cites W2261310161 @default.
- W3209860877 cites W2397830550 @default.
- W3209860877 cites W2478454054 @default.
- W3209860877 cites W2576289912 @default.
- W3209860877 cites W2584009249 @default.
- W3209860877 cites W2593172378 @default.
- W3209860877 cites W2593768305 @default.
- W3209860877 cites W2753211788 @default.
- W3209860877 cites W2758609995 @default.
- W3209860877 cites W2767106145 @default.
- W3209860877 cites W2786808285 @default.
- W3209860877 cites W2794022343 @default.
- W3209860877 cites W2795889831 @default.
- W3209860877 cites W2798414551 @default.
- W3209860877 cites W2883068149 @default.
- W3209860877 cites W2883386984 @default.
- W3209860877 cites W2936012732 @default.
- W3209860877 cites W2962019823 @default.
- W3209860877 cites W2962729993 @default.
- W3209860877 cites W2962793481 @default.
- W3209860877 cites W2962899390 @default.
- W3209860877 cites W2963073614 @default.
- W3209860877 cites W2963275094 @default.
- W3209860877 cites W2963693541 @default.
- W3209860877 cites W2963784072 @default.
- W3209860877 cites W2963826681 @default.
- W3209860877 cites W2964121744 @default.
- W3209860877 cites W2964266860 @default.
- W3209860877 cites W2964278684 @default.
- W3209860877 cites W2964285681 @default.
- W3209860877 cites W2964288524 @default.
- W3209860877 cites W3009290327 @default.
- W3209860877 cites W3017567979 @default.
- W3209860877 cites W3108146245 @default.
- W3209860877 cites W3163558475 @default.
- W3209860877 hasPublicationYear "2021" @default.
- W3209860877 type Work @default.
- W3209860877 sameAs 3209860877 @default.
- W3209860877 citedByCount "0" @default.
- W3209860877 crossrefType "posted-content" @default.
- W3209860877 hasAuthorship W3209860877A5042244876 @default.
- W3209860877 hasAuthorship W3209860877A5052695749 @default.
- W3209860877 hasAuthorship W3209860877A5055165096 @default.
- W3209860877 hasAuthorship W3209860877A5077258803 @default.
- W3209860877 hasAuthorship W3209860877A5085480111 @default.
- W3209860877 hasConcept C119857082 @default.
- W3209860877 hasConcept C12725497 @default.
- W3209860877 hasConcept C139807058 @default.
- W3209860877 hasConcept C153180895 @default.
- W3209860877 hasConcept C154945302 @default.
- W3209860877 hasConcept C160920958 @default.
- W3209860877 hasConcept C169760540 @default.
- W3209860877 hasConcept C2776434776 @default.
- W3209860877 hasConcept C31258907 @default.
- W3209860877 hasConcept C31395832 @default.
- W3209860877 hasConcept C41008148 @default.
- W3209860877 hasConcept C505870484 @default.
- W3209860877 hasConcept C86803240 @default.
- W3209860877 hasConcept C95623464 @default.
- W3209860877 hasConceptScore W3209860877C119857082 @default.
- W3209860877 hasConceptScore W3209860877C12725497 @default.
- W3209860877 hasConceptScore W3209860877C139807058 @default.
- W3209860877 hasConceptScore W3209860877C153180895 @default.
- W3209860877 hasConceptScore W3209860877C154945302 @default.
- W3209860877 hasConceptScore W3209860877C160920958 @default.
- W3209860877 hasConceptScore W3209860877C169760540 @default.
- W3209860877 hasConceptScore W3209860877C2776434776 @default.
- W3209860877 hasConceptScore W3209860877C31258907 @default.
- W3209860877 hasConceptScore W3209860877C31395832 @default.
- W3209860877 hasConceptScore W3209860877C41008148 @default.
- W3209860877 hasConceptScore W3209860877C505870484 @default.
- W3209860877 hasConceptScore W3209860877C86803240 @default.
- W3209860877 hasConceptScore W3209860877C95623464 @default.
- W3209860877 hasLocation W32098608771 @default.
- W3209860877 hasOpenAccess W3209860877 @default.
- W3209860877 hasPrimaryLocation W32098608771 @default.
- W3209860877 hasRelatedWork W123443654 @default.
- W3209860877 hasRelatedWork W1733349920 @default.
- W3209860877 hasRelatedWork W2020858209 @default.