Knowledge Distillation Based on Fitting Ground-Truth Distribution of Images

Autor: Jianze Li, Zhenhua Tang, Kai Chen, Zhenlei Cui

Publikováno v: Applied Sciences, Vol 14, Iss 8, p 3284 (2024)

Knowledge distillation based on the features from the penultimate layer allows the student (lightweight model) to efficiently mimic the internal feature outputs of the teacher (high-capacity model). However, the training data may not conform to the g

Externí odkaz: https://doaj.org/article/78e00af697094a4ab9c5bd2b23445047

CONVERGENCE OF GRADIENT-BASED BLOCK COORDINATE DESCENT ALGORITHMS FOR NONORTHOGONAL JOINT APPROXIMATE DIAGONALIZATION OF MATRICES.

Autor: JIANZE LI¹ lijianze@gmail.com, USEVICH, KONSTANTIN² konstantin.usevich@cnrs.fr, COMON, PIERRE³ pierre.comon@gipsa-lab.fr

Publikováno v: SIAM Journal on Matrix Analysis & Applications. 2023, Vol. 44 Issue 2, p592-621. 30p.

Data-Free Backdoor Removal Based on Channel Lipschitzness

Autor: Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu

Publikováno v: Lecture Notes in Computer Science ISBN: 9783031200649

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8f4885b544598a29a4b478bd94636057
https://doi.org/10.1007/978-3-031-20065-6_11

On the convergence of Jacobi-type algorithms for Independent Component Analysis

Autor: Pierre Comon, Konstantin Usevich, Jianze Li

Publikováno v: SAM 2020-11th Sensor Array and Multichannel Signal Processing Workshop, SAM 2020
SAM 2020-11th Sensor Array and Multichannel Signal Processing Workshop, SAM 2020, Jun 2020, Hangzhou (virtual), China. ⟨10.1109/SAM48682.2020.9104331⟩
SAM

Jacobi-type algorithms for simultaneous approximate diagonalization of real (or complex) symmetric tensors have been widely used in independent component analysis (ICA) because of their good performance. One natural way of choosing the index pairs in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70c0fd97da17fea193581e208ed0658f
https://hal.archives-ouvertes.fr/hal-02994725

Globally Convergent Jacobi-Type Algorithms for Simultaneous Orthogonal Symmetric Tensor Diagonalization

Autor: Jianze Li, Pierre Comon, Konstantin Usevich

Publikováno v: SIAM Journal on Matrix Analysis and Applications
SIAM Journal on Matrix Analysis and Applications, Society for Industrial and Applied Mathematics, 2018, 39 (1), pp.1-22. ⟨10.1137/17M1116295⟩
SIAM Journal on Matrix Analysis and Applications, 2018, 39 (1), pp.1-22. ⟨10.1137/17M1116295⟩

In this paper, we consider a family of Jacobi-type algorithms for simultaneous orthogonal diagonalization problem of symmetric tensors. For the Jacobi-based algorithm of [SIAM J. Matrix Anal. Appl., 2(34):651--672, 2013], we prove its global converge

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b12531e1454c524ca4538a9d6586f468
https://doi.org/10.1137/17m1116295