Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Rihuan Ke"'
Autor:
Rihuan Ke, Angelica I. Aviles-Rivero, Saurabh Pandey, Saikumar Reddy, Carola-Bibiane Schonlieb
Publikováno v:
Ke, R, Aviles-Rivero, A, Pandey, S, Reddy, S & Schönlieb, C-B 2022, ' A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation ', IEEE Transactions on Image Processing, vol. 31, pp. 1805-1815 . https://doi.org/10.1109/TIP.2022.3144036
Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high quality se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::729929c22e6113b3232c038c70390e7f
https://doi.org/10.1109/tip.2022.3144036
https://doi.org/10.1109/tip.2022.3144036
Publikováno v:
Linear and Multilinear Algebra. 70:3969-3981
In this paper, we study the properties of extreme points of slice-stochastic tensors, and present an analogue of the Birkhoff–von Neumann theorem for slice-stochastic tensors. Some equivalent chara...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23c34e878a95460abca5432860fd4439
https://doi.org/10.1080/03081087.2020.1859978
https://doi.org/10.1080/03081087.2020.1859978
Publikováno v:
Computers & Mathematics with Applications. 78:1008-1025
In this paper, we study a new tensor eigenvalue problem, which involves E - and S -eigenvalues as its special cases. Some theoretical results such as existence of an eigenvalue and the number of eigenvalues are given. For an application of the propos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f16b4d9b042af9af7051d14b01c640b6
https://doi.org/10.1016/j.camwa.2019.03.016
https://doi.org/10.1016/j.camwa.2019.03.016
Autor:
Xian-Ping Wu, Rihuan Ke
Publikováno v:
Numerical Algorithms. 83:1249-1257
In this paper, we define a backward error for the linear complementarity problem (LCP), and then present an expression of it which can be employed to examine the stability of algorithms solving the LCP. Some numerical examples are given to show the e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17543bd8d0eeb75cb2ec7e5339e2fa4e
https://doi.org/10.1007/s11075-019-00723-9
https://doi.org/10.1007/s11075-019-00723-9
Adaptive optics is a commonly used technique to correct the phase distortions caused by the Earth's atmosphere to improve the image quality of the ground-based imaging systems. However, the observe...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c9e5c773e7d3227e22e245f1795670e
In this paper, we consider an inverse problem with quasi-boundary value regularization for recovering a source term of the time fractional diffusion equations from the final observation data. In pa...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::665ec3af722ab922a90644ced7fcfa44
Autor:
Carola-Bibiane Schönlieb, Rihuan Ke
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(9)
Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of the restorat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dce7d3e3eadb7e7f3c2046174b3d3f23
https://pubmed.ncbi.nlm.nih.gov/33819148
https://pubmed.ncbi.nlm.nih.gov/33819148
Autor:
Nicolas Papadakis, Rihuan Ke, Carola-Bibiane Schönlieb, Aurélie Bugeau, Mark Kirkland, Peter Schuetz
Publikováno v:
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩
HAL
IEEE Transactions on Image Processing, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩
HAL
International audience; Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constrai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::84f005f182414424db2d06fde5c0a302
http://arxiv.org/abs/2005.13053
http://arxiv.org/abs/2005.13053
Publikováno v:
2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)
MLSP
MLSP
U-Nets have been established as a standard neural network architecture for image-to-image problems such as segmentation and inverse problems in imaging. For high-dimensional applications, as they for example appear in 3D medical imaging, U-Nets howev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::890b044c0fc34a3906833e6688ea7c73
Publikováno v:
SIAM Journal on Matrix Analysis & Applications; 2020, Vol. 41 Issue 4, p1857-1888, 32p