no code implementations • 23 Apr 2024 • Yang Chen, Ruituo Wu, Yipeng Liu, Ce Zhu
Implicit neural representations (INR) suffer from worsening spectral bias, which results in overly smooth solutions to the inverse problem.
no code implementations • 14 Mar 2024 • Yuan Fang, Yipeng Liu, Jie Chen, Zhen Long, Ao Li, Chong-Yung Chi, Ce Zhu
In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR).
1 code implementation • 14 Mar 2024 • Zhen Long, Qiyuan Wang, Yazhou Ren, Yipeng Liu, Ce Zhu
Specifically, we first construct the embedding feature tensor by stacking the embedding features of different views into a tensor and rotating it.
no code implementations • 6 Mar 2024 • Xinwei Ou, Ce Zhu, Xiaolin Huang, Yipeng Liu
Firstly, we reformulate the gradient preconditioning formula in the natural gradient descent (NGD) as a weighted sum of per-sample gradients using the Sherman-Morrison-Woodbury formula.
no code implementations • 13 Dec 2023 • Ruituo Wu, Jiani Liu, Ce Zhu, Anh-Huy Phan, Ivan V. Oseledets, Yipeng Liu
However, a substantial number of potential tensor permutations can lead to a tensor network with the same structure but varying expressive capabilities.
no code implementations • 25 Nov 2023 • Haolin He, Ce Zhu, Le Zhang, Yipeng Liu, Xiao Xu, Yuqian Chen, Leo Zekelman, Jarrett Rushmore, Yogesh Rathi, Nikos Makris, Lauren J. O'Donnell, Fan Zhang
The amygdala plays a vital role in emotional processing and exhibits structural diversity that necessitates fine-scale parcellation for a comprehensive understanding of its anatomico-functional correlations.
no code implementations • 17 Nov 2023 • Geyou Zhang, Ce Zhu, Kai Liu, Yipeng Liu
On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy.
1 code implementation • 30 Aug 2023 • Jiani Liu, Qinghua Tao, Ce Zhu, Yipeng Liu, Xiaolin Huang, Johan A. K. Suykens
In contrast to previous MTL frameworks, our decision function in the dual induces a weighted kernel function with a task-coupling term characterized by the similarities of the task-specific factors, better revealing the explicit relations across tasks in MTL.
13 code implementations • 22 Aug 2023 • Jiani Liu, Ce Zhu, Zhen Long, Yipeng Liu
Tensors, as high dimensional extensions of vectors, are considered as natural representations of high dimensional data.
no code implementations • 4 Jul 2023 • Yipeng Liu, Qi Yang, Yujie Zhang, Yiling Xu, Le Yang, Xiaozhong Xu, Shan Liu
Second, to reduce the significant domain discrepancy, we establish an intermediate domain, the description domain, based on insights from subjective experiments, by considering the domain relevance among samples located in the perception domain and learning a structured latent space.
1 code implementation • 16 May 2023 • Zhen Long, Ce Zhu, Jie Chen, Zihan Li, Yazhou Ren, Yipeng Liu
Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor.
1 code implementation • 13 May 2023 • Xinyu Lin, Yingjie Zhou, Xun Zhang, Yipeng Liu, Ce Zhu
Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations.
1 code implementation • 10 May 2023 • Xinyu Lin, Yingjie Zhou, Yipeng Liu, Ce Zhu
Line segment detection plays a cornerstone role in computer vision tasks.
no code implementations • 1 May 2023 • Yipeng Liu, Yingcong Lu, Weiting Ou, Zhen Long, Ce Zhu
Therefore, a pre-defined tensor decomposition may not fully exploit low rank information for a certain dataset, resulting in sub-optimal multi-view clustering performance.
no code implementations • 29 Apr 2023 • Xinyu Lin, Yingjie Zhou, Yipeng Liu, Ce Zhu
The challenges in existing methods and corresponding insights for potentially solving them are also provided to inspire researchers.
no code implementations • 22 Mar 2023 • Xinwei Ou, Zhangxin Chen, Ce Zhu, Yipeng Liu
However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not environmental-friendly with much power cost.
no code implementations • 4 Mar 2023 • Jiani Liu, Qinghua Tao, Ce Zhu, Yipeng Liu, Johan A. K. Suykens
Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement.
no code implementations • 3 Jan 2023 • Yipeng Liu, Qi Yang, Yiling Xu
Specifically, we use the attribute and geometry quantization steps of different compression methods (i. e., V-PCC, G-PCC and AVS) to infer the point cloud quality, assuming that the point clouds have no other distortions before compression.
no code implementations • 23 Oct 2022 • Yingcong Lu, Yipeng Liu, Zhen Long, Zhangxin Chen, Ce Zhu
To alleviate these problems, we propose a new tensor decomposition called Tucker-O-Minus Decomposition (TOMD) for multi-view clustering.
1 code implementation • CVPR 2022 • Qi Yang, Yipeng Liu, Siheng Chen, Yiling Xu, Jun Sun
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds.
Ranked #4 on Point Cloud Quality Assessment on WPC
no code implementations • 30 Sep 2021 • Hengling Zhao, Yipeng Liu, Xiaolin Huang, Ce Zhu
Tucker decomposition, Tensor Train (TT) and Tensor Ring (TR) are common decomposition for low rank compression of deep neural networks.
no code implementations • 15 Sep 2021 • Yipeng Liu, Qi Yang, Yiling Xu, Zhan Ma
Point cloud compression (PCC) has made remarkable achievement in recent years.
1 code implementation • 22 Apr 2021 • Jing Wu, Mingyi Zhou, Ce Zhu, Yipeng Liu, Mehrtash Harandi, Li Li
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
1 code implementation • 20 Mar 2021 • Tao Li, Lei Tan, Qinghua Tao, Yipeng Liu, Xiaolin Huang
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces.
no code implementations • 20 Jan 2021 • Zhonghao Zhang, Yipeng Liu, Xingyu Cao, Fei Wen, Ce Zhu
In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models.
1 code implementation • 22 Dec 2020 • Yipeng Liu, Qi Yang, Yiling Xu, Le Yang
Full-reference (FR) point cloud quality assessment (PCQA) has achieved impressive progress in recent years.
Ranked #5 on Point Cloud Quality Assessment on WPC
Blind Image Quality Assessment Point Cloud Quality Assessment
1 code implementation • 15 Sep 2020 • Jing Wu, Mingyi Zhou, Shuaicheng Liu, Yipeng Liu, Ce Zhu
A single perturbation can pose the most natural images to be misclassified by classifiers.
1 code implementation • 4 Aug 2020 • Fei Wen, Hewen Wei, Yipeng Liu, Peilin Liu
Furthermore, the new algorithms are applied to various 2D/3D registration problems.
no code implementations • 29 Jun 2020 • Zhen Long, Yipeng Liu, Sixing Zeng, Jiani Liu, Fei Wen, Ce Zhu
In this paper, we present a HSI restoration method named smooth and robust low rank tensor recovery.
no code implementations • 29 Jun 2020 • Zhen Long, Ce Zhu, Jiani Liu, Yipeng Liu
Low rank tensor ring model is powerful for image completion which recovers missing entries in data acquisition and transformation.
no code implementations • 21 Apr 2020 • Shenghan Wang, Yipeng Liu, Lanlan Feng, Ce Zhu
The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers, and it is the first time that frequency analysis is taken in tensor principal component analysis.
1 code implementation • 21 Apr 2020 • Zhonghao Zhang, Yipeng Liu, Jiani Liu, Fei Wen, Ce Zhu
By unfolding the iterative optimization algorithm for model-based methods onto networks, deep unfolding methods have the good interpretation of model-based methods and the high speed of classical deep network methods.
no code implementations • 28 Mar 2020 • Mingyi Zhou, Jing Wu, Yipeng Liu, Xiaolin Huang, Shuaicheng Liu, Xiang Zhang, Ce Zhu
Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.
2 code implementations • CVPR 2020 • Mingyi Zhou, Jing Wu, Yipeng Liu, Shuaicheng Liu, Ce Zhu
In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data.
no code implementations • 9 Jan 2020 • Huyan Huang, Yipeng Liu, Ce Zhu
To let coupled tensors help each other for missing component estimation, in this paper we utilize TR for coupled completion by sharing parts of the latent factors.
no code implementations • 31 Mar 2019 • Huyan Huang, Yipeng Liu, Ce Zhu
To further deal with its sensitivity to sparse component as it does in tensor principle component analysis, we propose robust tensor ring completion (RTRC), which separates latent low-rank tensor component from sparse component with limited number of measurements.
no code implementations • 12 Mar 2019 • Huyan Huang, Yipeng Liu, Ce Zhu
The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones.
1 code implementation • 8 Mar 2019 • Huyan Huang, Yipeng Liu, Ce Zhu
Tensor completion recovers a multi-dimensional array from a limited number of measurements.
no code implementations • 8 May 2018 • Chao Zhang, Ce Zhu, Jimin Xiao, Xun Xu, Yipeng Liu
Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.
no code implementations • 29 Mar 2017 • Zhengtao Wang, Ce Zhu, Zhiqiang Xia, Qi Guo, Yipeng Liu
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices.
no code implementations • 9 Feb 2017 • Qi Guo, Ce Zhu, Zhiqiang Xia, Zhengtao Wang, Yipeng Liu
In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion.
no code implementations • 15 Jan 2017 • Longxi Chen, Yipeng Liu, Ce Zhu
In this paper, we propose a new robust TPCA method to extract the princi- pal components of the multi-way data based on tensor singular value decomposition.
1 code implementation • 15 Aug 2016 • Zhiqiang Xia, Ce Zhu, Zhengtao Wang, Qi Guo, Yipeng Liu
We also demonstrate that style of images could be a combination of these texture primitives.
no code implementations • 30 Apr 2016 • Xinyu Lin, Ce Zhu, Qian Zhang, Yipeng Liu
Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications.
no code implementations • 29 Apr 2016 • Xinyu Lin, Ce Zhu, Yipeng Liu
Three dimensional (3D) interest point detection plays a fundamental role in 3D computer vision and graphics.
no code implementations • 29 Jun 2015 • Yipeng Liu, Maarten De Vos, Sabine Van Huffel
Significance: The proposed method enables successful compressed sensing of EEG signals even when the signals have no good sparse representation.
no code implementations • 20 Nov 2013 • Yipeng Liu
Based on the new signal model, a new optimization model for robust sparse signal reconstruction is proposed.