Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Chuanyun, Xu"'
Autor:
Yang Zhang, Danxia Hou, Chuanyun Xu, Heng Wang, Liping Peng, Xinghai Yuan, Xuanpeng Zhang, Gang Li, Song Sun
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-15 (2024)
Abstract Sand gradation is an important reference factor for concrete proportion design, which has a significant impact on the strength and workability of concrete. The efficiency of using the traditional vibrating sieving method to measure the grada
Externí odkaz:
https://doaj.org/article/4b6147ade4eb4febbeb38a857d7171a8
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-10 (2024)
Abstract Generally, the recognition performance of lightweight models is often lower than that of large models. Knowledge distillation, by teaching a student model using a teacher model, can further enhance the recognition accuracy of lightweight mod
Externí odkaz:
https://doaj.org/article/ecd0eee717154d368d1e4fe63f6c62ee
Publikováno v:
Bioengineering, Vol 11, Iss 7, p 686 (2024)
Automated detection of cervical lesion cell/clumps in cervical cytological images is essential for computer-aided diagnosis. In this task, the shape and size of the lesion cell/clumps appeared to vary considerably, reducing the detection performance
Externí odkaz:
https://doaj.org/article/8e3e8ef7b78e4ddcb05353a4b4b7fa62
Publikováno v:
Applied Sciences, Vol 14, Iss 12, p 5217 (2024)
Learning a deep model from small data is an opening and challenging problem. In high-dimensional spaces, few samples only occupy an extremely small portion of the space, often exhibiting sparsity issues. Classifying in this globally sparse sample spa
Externí odkaz:
https://doaj.org/article/315b7befb87e498382655688cef9c893
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-15 (2023)
Abstract Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus image
Externí odkaz:
https://doaj.org/article/1a2e40d997724e0f92bc38bb5839e5bd
Publikováno v:
Applied Sciences, Vol 14, Iss 4, p 1599 (2024)
Few-shot learning refers to training a model with a few labeled data to effectively recognize unseen categories. Recently, numerous approaches have been suggested to improve the extraction of abundant feature information at hierarchical layers or mul
Externí odkaz:
https://doaj.org/article/a155fe3293f4468c953873569a221a46
Publikováno v:
IEEE Open Journal of Intelligent Transportation Systems, Vol 3, Pp 340-350 (2022)
Foreground segmentation aims at extracting moving objects from the background in a robust manner under various challenging scenarios. The deep learning-based methods have achieved remarkable improvement in this field. These methods produce semantical
Externí odkaz:
https://doaj.org/article/2911292ebef84c39a399cdf1c7271ee7
Publikováno v:
Fire, Vol 6, Iss 6, p 225 (2023)
Fire perception based on machine vision is essential for improving social safety. Object recognition based on deep learning has become the mainstream smoke and flame recognition method. However, the existing anchor-based smoke and flame recognition a
Externí odkaz:
https://doaj.org/article/7765712e0b694c7483862c5efaf031af
Publikováno v:
Biomimetics, Vol 7, Iss 4, p 195 (2022)
Current deep-learning-based cervical cell classification methods suffer from parameter redundancy and poor model generalization performance, which creates challenges for the intelligent classification of cervical cytology smear images. In this paper,
Externí odkaz:
https://doaj.org/article/dbe48cee87f9435a822ea8db99b27285
Publikováno v:
Diagnostics, Vol 12, Iss 10, p 2477 (2022)
Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have b
Externí odkaz:
https://doaj.org/article/5bd07f3870f64b20aebe38d459d76bb2