Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Xinzheng Xu"'
Publikováno v:
Mathematical Biosciences and Engineering, Vol 20, Iss 10, Pp 17905-17918 (2023)
Complementary label learning (CLL) is a type of weakly supervised learning method that utilizes the category of samples that do not belong to a certain class to learn their true category. However, current CLL methods mainly rely on rewriting classifi
Externí odkaz:
https://doaj.org/article/7271f294c8ec47c4aaca4f4032c8737a
Publikováno v:
Electronic Research Archive, Vol 31, Iss 7, Pp 4185-4215 (2023)
Convolutional neural networks (CNNs) utilize local translation invariance in the Euclidean domain and have remarkable achievements in computer vision tasks. However, there are many data types with non-Euclidean structures, such as social networks, ch
Externí odkaz:
https://doaj.org/article/56929fc4988843aeb77a0f48ad5ed155
Publikováno v:
Electronic Research Archive, Vol 31, Iss 6, Pp 3187-3199 (2023)
In the lightweight convolutional neural network model, the pointwise convolutional structure occupies most of the parameters and computation amount of the model. Therefore, improving the pointwise convolution structure is the best choice to optimize
Externí odkaz:
https://doaj.org/article/c38b6fc97eaf4a08a6db2bf87490bd12
Publikováno v:
Mathematical Biosciences and Engineering, Vol 20, Iss 4, Pp 6191-6214 (2023)
With the increasing application of deep neural networks, their performance requirements in various fields are increasing. Deep neural network models with higher performance generally have a high number of parameters and computation (FLOPs, Floating P
Externí odkaz:
https://doaj.org/article/aa652d58d4c54b98b7c5ccc1f1fa307e
Publikováno v:
Mathematical Biosciences and Engineering, Vol 20, Iss 4, Pp 6551-6590 (2023)
Small object detection (SOD) is significant for many real-world applications, including criminal investigation, autonomous driving and remote sensing images. SOD has been one of the most challenging tasks in computer vision due to its low resolution
Externí odkaz:
https://doaj.org/article/d1cc36066fd84d6fb44c566bdf7af65c
Publikováno v:
Mathematical Biosciences and Engineering, Vol 19, Iss 12, Pp 12232-12246 (2022)
In recent years, deep convolutional neural network (CNN) has been applied more and more increasingly used in computer vision, natural language processing and other fields. At the same time, low-power platforms have more and more significant requireme
Externí odkaz:
https://doaj.org/article/38f15dd63c464b659a90f5f17f09b60e
Publikováno v:
Healthcare, Vol 10, Iss 11, p 2300 (2022)
Ordinal multi-instance learning (OMIL) deals with the weak supervision scenario wherein instances in each training bag are not only multi-class but also have rank order relationships between classes, such as breast cancer, which has become one of the
Externí odkaz:
https://doaj.org/article/9ad2eb59f7f44b5e97f7634e62363e6f
Publikováno v:
Healthcare, Vol 10, Iss 11, p 2170 (2022)
Bone age assessment (BAA) based on X-ray imaging of the left hand and wrist can accurately reflect the degree of the body’s physiological development and physical condition. However, the traditional manual evaluation method relies too much on ineff
Externí odkaz:
https://doaj.org/article/71d6162f98cc4bcb885e6e3200b340db
Publikováno v:
Multimedia Tools and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e95f0c7a5c399989852ef5b94ccc33c
https://doi.org/10.1007/s11042-023-15624-2
https://doi.org/10.1007/s11042-023-15624-2
Publikováno v:
Multimedia Tools and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96a2ab1161dd2ff9e78eb9be65b2e351
https://doi.org/10.1007/s11042-023-15057-x
https://doi.org/10.1007/s11042-023-15057-x