Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Yemin Shi"'
Autor:
Zhongzhi Yu, Yemin Shi
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-9 (2023)
Abstract In computer-aided diagnosis (CAD), diagnosing untrained diseases as known categories will cause serious medical accidents, which makes it crucial to distinguish the new class (open set) meanwhile preserving the known classes (closed set) per
Externí odkaz:
https://doaj.org/article/f6a153d71f254db69229c58286db0b91
Autor:
Zhongzhi Yu, Yemin Shi
Publikováno v:
IEEE Access, Vol 10, Pp 4063-4071 (2022)
This paper presents a novel network compression framework, Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance
Externí odkaz:
https://doaj.org/article/d607107c553b41d49daca80a0a731f82
Publikováno v:
PLoS Computational Biology, Vol 5, Iss 9, p e1000514 (2009)
Simian virus 40 large tumor antigen (LTag) is an efficient helicase motor that unwinds and translocates DNA. The DNA unwinding and translocation of LTag is powered by ATP binding and hydrolysis at the nucleotide pocket between two adjacent subunits o
Externí odkaz:
https://doaj.org/article/6ab5c0b29a0249d6b6263dd552198ee9
Publikováno v:
AAAI
Low bit-width model quantization is highly desirable when deploying a deep neural network on mobile and edge devices. Quantization is an effective way to reduce the model size with low bit-width weight representation. However, the unacceptable accura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::489d9fd7cb52e324671775a645328cec
https://doi.org/10.1609/aaai.v34i04.6134
https://doi.org/10.1609/aaai.v34i04.6134
Publikováno v:
IEEE Transactions on Multimedia. 21:3194-3204
Intuitively, we can think of object recognition and attribute prediction as correlated tasks. However, they appeared to conflict in a simple two-branch multi-task framework (a category branch and an attribute branch) with a shared backbone part (conv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::666e81cefb3ba0738415ba55b4df70b2
https://doi.org/10.1109/tmm.2019.2919469
https://doi.org/10.1109/tmm.2019.2919469
Publikováno v:
2021 IEEE International Conference on Image Processing (ICIP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16ead235981edceaa3690423fab85c3c
https://doi.org/10.1109/icip42928.2021.9506563
https://doi.org/10.1109/icip42928.2021.9506563
Autor:
Hong Zhao, Weihang Ma, Jianhua Hu, Jifang Sheng, Ruihong Zhao, Jianke Ma, Lanjuan Li, Xuan Zhang, Yemin Shi
Publikováno v:
Expert Review of Gastroenterology & Hepatology. 13:263-269
Upper gastrointestinal hemorrhage (UGH) is a life-threatening complication in patients with cirrhosis; however, data regarding the role of UGH in acute-on-chronic liver failure (ACLF) are limited.A prospective, observational cohort study was performe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::194dd0acdda3ca295127adb547290262
https://doi.org/10.1080/17474124.2019.1567329
https://doi.org/10.1080/17474124.2019.1567329
Publikováno v:
MIPR
In this paper, we introduce a new channel pruning method called Similarity-aware Channel Pruning to simultaneously accelerate and compress CNNs. Most existing channel pruning methods focus on pruning channels by the filter saliency. However, small ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ceee50da9bd1c8e4b27899e5a6af2fd
https://doi.org/10.1109/mipr49039.2020.00037
https://doi.org/10.1109/mipr49039.2020.00037
Autor:
Guangyao Chen, Tiejun Huang, Yaowei Wang, Mingkui Tan, Lechun Zhang, Yonghong Tian, Yemin Shi, Quan Zhang
Publikováno v:
MIPR
Many deep neural network compression algorithms need to fine-tune on source dataset, which makes them unpractical when the source datasets are unavailable. Although data-free methods can overcome this problem, they often suffer from a huge loss of ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f82bc35539575aca939dfd060f12c55e
https://doi.org/10.1109/mipr49039.2020.00040
https://doi.org/10.1109/mipr49039.2020.00040
Publikováno v:
Scientific Reports
Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
Most of the existing recognition algorithms are proposed for closed set scenarios, where all categories are known beforehand. However, in practice, recognition is essentially an open set problem. There are categories we know called “knowns”, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac7fe9a2fcc39f13593474cbafd0f0f6
https://doi.org/10.1038/s41598-020-63649-6
https://doi.org/10.1038/s41598-020-63649-6