이미지를 강인하게 인식하는 보조 노이즈 전파 기법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 196
  • Download : 0
DC FieldValueLanguage
dc.contributor.author이우주ko
dc.contributor.author홍다솔ko
dc.contributor.author이인균ko
dc.contributor.author명현ko
dc.date.accessioned2023-03-22T07:02:05Z-
dc.date.available2023-03-22T07:02:05Z-
dc.date.created2023-03-20-
dc.date.issued2023-02-15-
dc.identifier.citation제 18회 한국로봇종합학술대회 (KRoC 2023)-
dc.identifier.urihttp://hdl.handle.net/10203/305749-
dc.description.abstractIn this study, we propose an auxiliary noise propagation module that is robust to an unstructured environment. Deep neural networks show high classification performance when training and testing data are drawn from the independent and identical distribution. However, deep neural networks show significantly low performance for the out-of-distribution data. Augmented noisy images could be the solution, but they degrade the model performance for the original data distribution. Our proposed model balances and improves performance for both cases. Our model propagates the original images to the original batch normalization layer and augmented noisy images to the auxiliary batch normalization layer separately. Separate batch normalization layers enforce the model to learn various features and improve the robustness for out-of-distribution data. Auxiliary noise propagation is trained on CIFAR-10 and the performance of the module is evaluated on the CIFAR-10-C. Experimental results show that the proposed auxiliary noise propagation improves the robustness for out-of-distribution data.-
dc.languageKorean-
dc.publisher한국로봇학회 (KROS)-
dc.title이미지를 강인하게 인식하는 보조 노이즈 전파 기법-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationname제 18회 한국로봇종합학술대회 (KRoC 2023)-
dc.identifier.conferencecountryKO-
dc.identifier.conferencelocation휘닉스 평창-
dc.contributor.localauthor명현-
dc.contributor.nonIdAuthor홍다솔-
dc.contributor.nonIdAuthor이인균-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0