Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Yasuto Yokota"'
Publikováno v:
2022 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c45ab2bd6c91fcfb1ba3133f720db29
https://doi.org/10.1109/icip46576.2022.9897419
https://doi.org/10.1109/icip46576.2022.9897419
Publikováno v:
2022 26th International Conference on Pattern Recognition (ICPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3670175172e5b6cf0044084ecc07d31b
https://doi.org/10.1109/icpr56361.2022.9956437
https://doi.org/10.1109/icpr56361.2022.9956437
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Existing unsupervised domain adaptation (UDA) studies focus on transferring knowledge in an offline manner. However, many tasks involve online requirements, especially in real-time systems. In this paper, we discuss Online UDA (OUDA) which assumes th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e73078346401ba3562f3687b214e3ae
https://doi.org/10.24963/ijcai.2022/410
https://doi.org/10.24963/ijcai.2022/410
Publikováno v:
CIKM
Unsupervised domain adaptation (UDA) methods aim to transfer knowledge from a labeled source domain to an unlabeled target domain. Most existing UDA methods try to learn domain-invariant features so that the classifier trained by the source labels ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6640a37241d7db9e3cd1b0a45fad2b99
https://doi.org/10.1145/3459637.3482238
https://doi.org/10.1145/3459637.3482238
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5a0ce3696e9497e9bd05887c3a3c9d7
https://doi.org/10.1109/icip42928.2021.9506124
https://doi.org/10.1109/icip42928.2021.9506124
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7fa2e82b265bd2b6961df066b38df8e
https://doi.org/10.1109/icip42928.2021.9506056
https://doi.org/10.1109/icip42928.2021.9506056
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d3c487c5ce2d4aaee16ac922db85f2b
https://doi.org/10.1109/icip42928.2021.9506074
https://doi.org/10.1109/icip42928.2021.9506074
Publikováno v:
IEEE Transactions on Instrumentation and Measurement. :1-1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4d43e517583462aec4bb95c2783af1a
https://doi.org/10.1109/tim.2022.3221131
https://doi.org/10.1109/tim.2022.3221131
Publikováno v:
SII
It is a big problem that a model of deep learning for a picking robot needs many labeled images. Operating costs of retraining a model becomes very expensive because the object shape of a product or a part often is changed in a factory. It is importa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::378196d2cbc94a9063ebda7cab5bb4e2
https://doi.org/10.1109/sii46433.2020.9025946
https://doi.org/10.1109/sii46433.2020.9025946
Publikováno v:
SII
Self-supervised learning methods are attractive candidates for automatic object picking. However, the trial samples lack the complete ground truth because the observable parts of the agent are limited. That is, the information contained in the trial
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::892ce1ec093fea762d6a2d76cb1aa7a5
https://doi.org/10.1109/sii46433.2020.9025845
https://doi.org/10.1109/sii46433.2020.9025845