Zobrazeno 1 - 10
of 222
pro vyhledávání: '"mode collapse"'
Publikováno v:
Visual Informatics, Vol 8, Iss 1, Pp 15-25 (2024)
Medical image generation has recently garnered significant interest among researchers. However, the primary generative models, such as Generative Adversarial Networks (GANs), often encounter challenges during training, including mode collapse. To add
Externí odkaz:
https://doaj.org/article/e3dbfe4ea80a409a8d56ed198930b192
Publikováno v:
Machine Learning and Knowledge Extraction, Vol 5, Iss 4, Pp 1456-1473 (2023)
Generative Adversarial Networks are powerful generative models that are used in different areas and with multiple applications. However, this type of model has a training problem called mode collapse. This problem causes the generator to not learn th
Externí odkaz:
https://doaj.org/article/55da95072b844c398346b45379662574
Autor:
Muhammad Irfan, Zohaib Mushtaq, Nabeel Ahmed Khan, Faisal Althobiani, Salim Nasar Faraj Mursal, Saifur Rahman, Muawia Abdelkafi Magzoub, Muhammad Armghan Latif, Imran Khan Yousufzai
Publikováno v:
IEEE Access, Vol 11, Pp 118253-118267 (2023)
Bearing faults are critical in machinery; their early detection is vital to prevent costly breakdowns and ensure operational safety. This study presents a pioneering take on addressing the challenges of imbalanced datasets in bearing fault diagnosis.
Externí odkaz:
https://doaj.org/article/6cf513e0690943738edcb69b2e72d552
Autor:
Issam Boukhennoufa, Delaram Jarchi, Xiaojun Zhai, Victor Utti, Saeid Sanei, Tracey K. M. Lee, Jo Jackson, Klaus D. McDonald-Maier
Publikováno v:
IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol 31, Pp 2676-2687 (2023)
The application of machine learning-based tele-rehabilitation faces the challenge of limited availability of data. To overcome this challenge, data augmentation techniques are commonly employed to generate synthetic data that reflect the configuratio
Externí odkaz:
https://doaj.org/article/ae283b5919754709a7fc37274deaa2c1
Publikováno v:
IEEE Access, Vol 11, Pp 43276-43285 (2023)
Generative adversarial networks (GANs) are a powerful tool for synthesizing realistic images, but they can be difficult to train and are prone to instability and mode collapse. This paper proposes a new model called Identity Generative Adversarial Ne
Externí odkaz:
https://doaj.org/article/31c78a5325a14f83bdf1f6ad93da00b8
Autor:
Wei Li, Yongchuan Tang
Publikováno v:
Applied Sciences, Vol 14, Iss 2, p 579 (2024)
In this paper, we propose the Soft Generative Adversarial Network (SoftGAN), a strategy that utilizes a dynamic borderline softening mechanism to train Generative Adversarial Networks. This mechanism aims to solve the mode collapse problem and enhanc
Externí odkaz:
https://doaj.org/article/43a93a20e7be460cb6801603fd676302
Publikováno v:
Entropy, Vol 25, Iss 12, p 1657 (2023)
Generative Adversarial Nets (GANs) are a kind of transformative deep learning framework that has been frequently applied to a large variety of applications related to the processing of images, video, speech, and text. However, GANs still suffer from
Externí odkaz:
https://doaj.org/article/6596ea3772554be1b1543ae9243def66
Publikováno v:
هوش محاسباتی در مهندسی برق, Vol 13, Iss 3, Pp 75-86 (2022)
Generative models try to obtain a probability distribution that is similar to that of observed data. Two different solutions have been proposed in this regard in recent years: one is to minimize the divergence (distance) between the two distributions
Externí odkaz:
https://doaj.org/article/e2060122d316459998aee99359a48b22
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:
Sensors, Vol 23, Iss 17, p 7338 (2023)
As one of the representative models in the field of image generation, generative adversarial networks (GANs) face a significant challenge: how to make the best trade-off between the quality of generated images and training stability. The U-Net based
Externí odkaz:
https://doaj.org/article/8fd39d68eedf402db37862b37511c4a1