Zobrazeno 1 - 10
of 465
pro vyhledávání: '"self-distillation"'
Autor:
Ratana Charoenpanyakul, Veerayuth Kittichai, Songpol Eiamsamang, Patchara Sriwichai, Natchapon Pinetsuksai, Kaung Myat Naing, Teerawat Tongloy, Siridech Boonsang, Santhad Chuwongin
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-20 (2024)
Abstract Traditional mosquito identification methods, relied on microscopic observation and morphological characteristics, often require significant expertise and experience, which can limit their effectiveness. This study introduces a self-supervise
Externí odkaz:
https://doaj.org/article/180b062b2a844c6ebe77d702b92a1eee
Autor:
Kun Liu, Xuanqi Zhang, Haiyun Yu, Jie Song, Tianxiao Xu, Min Li, Chang Liu, Shuang Liu, Yucheng Wang, Zhenyu Cui, Kun Yang
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-14 (2024)
Abstract Urolithiasis is a leading urological disorder where accurate preoperative identification of stone types is critical for effective treatment. Deep learning has shown promise in classifying urolithiasis from CT images, yet faces challenges wit
Externí odkaz:
https://doaj.org/article/8390ab3b2ae54a51a0be14460d416cd5
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 6, Pp 8043-8061 (2024)
Abstract A multi-exit network is an important technique for achieving adaptive inference by dynamically allocating computational resources based on different input samples. The existing works mainly treat the final classifier as the teacher, enhancin
Externí odkaz:
https://doaj.org/article/5bf8dbd360244ddc89dd9b47678aa461
Publikováno v:
Machine Learning with Applications, Vol 18, Iss , Pp 100605- (2024)
Deep learning has achieved notable success across academia, medicine, and industry. Its ability to identify complex patterns in large-scale data and to manage millions of parameters has made it highly advantageous. However, deploying deep learning mo
Externí odkaz:
https://doaj.org/article/ba1c9bcebde040e69bb558e1d98d3b42
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 5, Pp 6545-6557 (2024)
Abstract Self-distillation method guides the model learning via transferring knowledge of the model itself, which has shown the advantages in object segmentation. However, it has been proved that uncertain pixels with predicted probability close to 0
Externí odkaz:
https://doaj.org/article/a1657d44e824414e91a6412015c964b8
Autor:
Dong, Chi a, 1, Wu, Yujiao a, 1, Sun, Bo b, 1, Bo, Jiayi c, Huang, Yufei a, Geng, Yikang a, Zhang, Qianhui a, Liu, Ruixiang a, Guo, Wei c, ⁎, Wang, Xingling d, ⁎, Jiang, Xiran a, ⁎
Publikováno v:
In Computerized Medical Imaging and Graphics January 2025 119
Publikováno v:
In Neurocomputing 14 February 2025 618
Autor:
Muyang Sun, Haitao Jia
Publikováno v:
Journal of Engineering and Applied Science, Vol 71, Iss 1, Pp 1-20 (2024)
Abstract Zero-shot learning represents a formidable paradigm in machine learning, wherein the crux lies in distilling and generalizing knowledge from observed classes to novel ones. The objective is to identify unfamiliar objects that were not includ
Externí odkaz:
https://doaj.org/article/ce4d893f35fe447d8bfe4758a63ebaf7
Publikováno v:
IEEE Access, Vol 12, Pp 184883-184895 (2024)
The time-dimensional self-distillation seeks to transfer knowledge from earlier historical models to subsequent ones with minimal computational overhead. This enables model self-augmentation without the need for large teacher models, making it partic
Externí odkaz:
https://doaj.org/article/3b184faa9918494e95e9cc31cf17bf28
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 17075-17086 (2024)
Massive tree dieback events triggered by various disturbance agents, such as insect outbreaks, pests, fires, and windstorms, have recently compromised the health of forests in numerous countries with a significant impact on ecosystems. The inventory
Externí odkaz:
https://doaj.org/article/e1e7a9af55fa49efa114f3895df58b7c