Zobrazeno 1 - 10
of 604
pro vyhledávání: '"class incremental learning"'
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 15845-15861 (2024)
Synthetic aperture radar automatic target recognition (SAR ATR) has ushered in a new era dominated by deep-learning (DL) techniques. However, the DL-based recognition systems inevitably confront catastrophic forgetting for learned knowledge and overf
Externí odkaz:
https://doaj.org/article/5cd75c424a3148bb8edf41ccfd758c5b
Publikováno v:
Zhihui kongzhi yu fangzhen, Vol 46, Iss 1, Pp 44-54 (2024)
In view of the catastrophic forgetting of previous knowledge in class incremental learning for image classification, existing replay-based methods focus on memory updating and sampling, while overlooking the feature relationships between old and new
Externí odkaz:
https://doaj.org/article/b4085dc027a4465881fbe422f3929c73
Autor:
Davide Di Monda, Antonio Montieri, Valerio Persico, Pasquale Voria, Matteo De Ieso, Antonio Pescape
Publikováno v:
IEEE Open Journal of the Communications Society, Vol 5, Pp 6736-6757 (2024)
In today’s digital landscape, critical services are increasingly dependent on network connectivity, thus cybersecurity has become paramount. Indeed, the constant escalation of cyberattacks, including zero-day exploits, poses a significant threat. W
Externí odkaz:
https://doaj.org/article/bd4edb29be314e6ea238dd0743948967
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 13602-13615 (2024)
Applying synthetic aperture radar automatic target recognition (SAR ATR) in open scenario based on deep learning (DL) is challenging due to the difficulty in incrementally recognizing new targets with limited samples. To address this challenge, we in
Externí odkaz:
https://doaj.org/article/a93c7cff89bb405cbd05523e8a101325
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 4408-4420 (2024)
In this article, we explore a cutting-edge concept known as class incremental learning (CIL) in novel category discovery for synthetic aperture radar (SAR) targets (CNTs). This innovative task involves the challenge of identifying categories within u
Externí odkaz:
https://doaj.org/article/d21610ac9b0c4cff868e7292f8546799
Publikováno v:
Medicine in Novel Technology and Devices, Vol 22, Iss , Pp 100308- (2024)
Hand gesture recognition (HGR) plays a vital role in human-computer interaction. The integration of high-density surface electromyography (HD-sEMG) and deep neural networks (DNNs) has significantly improved the robustness and accuracy of HGR systems.
Externí odkaz:
https://doaj.org/article/e307029c33ed4b1baf8b6e52642731df
Autor:
In-Ug Yoon, Jong-Hwan Kim
Publikováno v:
IEEE Access, Vol 11, Pp 140626-140635 (2023)
The main challenge of FSCIL is the trade-off between underfitting to a new session task and preventing forgetting the knowledge for earlier sessions. In this paper, we reveal that the angular space occupied by the features within the embedded area is
Externí odkaz:
https://doaj.org/article/d7c8ded714f9431ea0f02a402645d99f
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
PeerJ Computer Science, Vol 9, p e1583 (2023)
When a well-trained model learns a new class, the data distribution differences between the new and old classes inevitably cause catastrophic forgetting in order to perform better in the new class. This behavior differs from human learning. In this a
Externí odkaz:
https://doaj.org/article/8a09b57648ad4dd7b491a057c95256ad