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.
3 code implementations • 22 Apr 2024 • Xiaoning Liu, Zongwei Wu, Ao Li, Florin-Alexandru Vasluianu, Yulun Zhang, Shuhang Gu, Le Zhang, Ce Zhu, Radu Timofte, Zhi Jin, Hongjun Wu, Chenxi Wang, Haitao Ling, Yuanhao Cai, Hao Bian, Yuxin Zheng, Jing Lin, Alan Yuille, Ben Shao, Jin Guo, Tianli Liu, Mohao Wu, Yixu Feng, Shuo Hou, Haotian Lin, Yu Zhu, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang, Qingsen Yan, Wenbin Zou, Weipeng Yang, Yunxiang Li, Qiaomu Wei, Tian Ye, Sixiang Chen, Zhao Zhang, Suiyi Zhao, Bo wang, Yan Luo, Zhichao Zuo, Mingshen Wang, Junhu Wang, Yanyan Wei, Xiaopeng Sun, Yu Gao, Jiancheng Huang, Hongming Chen, Xiang Chen, Hui Tang, Yuanbin Chen, Yuanbo Zhou, Xinwei Dai, Xintao Qiu, Wei Deng, Qinquan Gao, Tong Tong, Mingjia Li, Jin Hu, Xinyu He, Xiaojie Guo, sabarinathan, K Uma, A Sasithradevi, B Sathya Bama, S. Mohamed Mansoor Roomi, V. Srivatsav, Jinjuan Wang, Long Sun, Qiuying Chen, Jiahong Shao, Yizhi Zhang, Marcos V. Conde, Daniel Feijoo, Juan C. Benito, Alvaro García, Jaeho Lee, Seongwan Kim, Sharif S M A, Nodirkhuja Khujaev, Roman Tsoy, Ali Murtaza, Uswah Khairuddin, Ahmad 'Athif Mohd Faudzi, Sampada Malagi, Amogh Joshi, Nikhil Akalwadi, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Wenyi Lian, Wenjing Lian, Jagadeesh Kalyanshetti, Vijayalaxmi Ashok Aralikatti, Palani Yashaswini, Nitish Upasi, Dikshit Hegde, Ujwala Patil, Sujata C, Xingzhuo Yan, Wei Hao, Minghan Fu, Pooja Choksy, Anjali Sarvaiya, Kishor Upla, Kiran Raja, Hailong Yan, Yunkai Zhang, Baiang Li, Jingyi Zhang, Huan Zheng
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
no code implementations • 10 Apr 2024 • Geyou Zhang, Ce Zhu, Kai Liu
Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property.
no code implementations • 6 Apr 2024 • Yijie Li, Wei zhang, Ye Wu, Li Yin, Ce Zhu, Yuqian Chen, Suheyla Cetin-Karayumak, Kang Ik K Cho, Leo R. Zekelman, Jarrett Rushmore, Yogesh Rathi, Nikos Makris, Lauren J. O'Donnell, Fan Zhang
However, a comprehensive investigation into WM fiber tracts between Eastern and Western populations is challenged due to the lack of a cross-population WM atlas and the large site-specific variability of dMRI data.
1 code implementation • 25 Mar 2024 • Zhiwei Lin, Zhe Liu, Zhongyu Xia, Xinhao Wang, Yongtao Wang, Shengxiang Qi, Yang Dong, Nan Dong, Le Zhang, Ce Zhu
In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders.
Ranked #2 on 3D Object Detection on nuscenes Camera-Radar
no code implementations • 15 Mar 2024 • Xiaoning Liu, Ao Li, Zongwei Wu, Yapeng Du, Le Zhang, Yulun Zhang, Radu Timofte, Ce Zhu
Leveraging Transformer attention has led to great advancements in HDR deghosting.
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
Second-order optimization techniques have the potential to achieve faster convergence rates compared to first-order methods through the incorporation of second-order derivatives or statistics.
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.
no code implementations • 24 Sep 2023 • Xinyue Chen, Jie Xu, Yazhou Ren, Xiaorong Pu, Ce Zhu, Xiaofeng Zhu, Zhifeng Hao, Lifang He
Second, the storage and usage of data from multiple clients in a distributed environment can lead to incompleteness of multi-view data.
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.
1 code implementation • ICCV 2023 • Ao Li, Le Zhang, Yun Liu, Ce Zhu
Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies.
Ranked #26 on Image Super-Resolution on Set14 - 4x upscaling
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.
1 code implementation • 19 Dec 2022 • Fanxing Liu, Cheng Zeng, Le Zhang, Yingjie Zhou, Qing Mu, Yanru Zhang, Ling Zhang, Ce Zhu
We would like to answer the following questions: (1)How is the performance of time series anomaly detection algorithms when meeting federated learning?
no code implementations • 14 Dec 2022 • Le Zhang, Qibin Hou, Yun Liu, Jia-Wang Bian, Xun Xu, Joey Tianyi Zhou, Ce Zhu
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
2 code implementations • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsik Choe, Jinwoo Jeong, Sungjei Kim, Maciej Smyl, Tomasz Latkowski, Pawel Kubik, Michal Sokolski, Yujie Ma, Jiahao Chao, Zhou Zhou, Hongfan Gao, Zhengfeng Yang, Zhenbing Zeng, Zhengyang Zhuge, Chenghua Li, Dan Zhu, Mengdi Sun, Ran Duan, Yan Gao, Lingshun Kong, Long Sun, Xiang Li, Xingdong Zhang, Jiawei Zhang, Yaqi Wu, Jinshan Pan, Gaocheng Yu, Jin Zhang, Feng Zhang, Zhe Ma, Hongbin Wang, Hojin Cho, Steve Kim, Huaen Li, Yanbo Ma, Ziwei Luo, Youwei Li, Lei Yu, Zhihong Wen, Qi Wu, Haoqiang Fan, Shuaicheng Liu, Lize Zhang, Zhikai Zong, Jeremy Kwon, Junxi Zhang, Mengyuan Li, Nianxiang Fu, Guanchen Ding, Han Zhu, Zhenzhong Chen, Gen Li, Yuanfan Zhang, Lei Sun, Dafeng Zhang, Neo Yang, Fitz Liu, Jerry Zhao, Mustafa Ayazoglu, Bahri Batuhan Bilecen, Shota Hirose, Kasidis Arunruangsirilert, Luo Ao, Ho Chun Leung, Andrew Wei, Jie Liu, Qiang Liu, Dahai Yu, Ao Li, Lei Luo, Ce Zhu, Seongmin Hong, Dongwon Park, Joonhee Lee, Byeong Hyun Lee, Seunggyu Lee, Se Young Chun, Ruiyuan He, Xuhao Jiang, Haihang Ruan, Xinjian Zhang, Jing Liu, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
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 • The 31st International Joint Conference On Artificial Intelligence 2022 • Hu Wang, Mao Ye, Xiatian Zhu, Shuai Li, Ce Zhu, Xue Li
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions.
1 code implementation • 17 Mar 2022 • Zhiyuan Zha, Bihan Wen, Xin Yuan, Saiprasad Ravishankar, Jiantao Zhou, Ce Zhu
Furthermore, we present a unified framework for incorporating various GSR and LR models and discuss the relationship between GSR and LR models.
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.
2 code implementations • 22 May 2021 • Yingjie Zhou, Xucheng Song, Yanru Zhang, Fanxing Liu, Ce Zhu, Lingqiao Liu
Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data.
Supervised Anomaly Detection Weakly-supervised Anomaly Detection
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 • 3 Mar 2021 • Honggang Chen, Xiaohai He, Linbo Qing, Yuanyuan Wu, Chao Ren, Ce Zhu
More specifically, this review covers the critical publically available datasets and assessment metrics for RSISR, and four major categories of RSISR methods, namely the degradation modeling-based RSISR, image pairs-based RSISR, domain translation-based RSISR, and self-learning-based RSISR.
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 • 29 Oct 2020 • Feng Li, Runmin Cong, Huihui Bai, Yifan He, Yao Zhao, Ce Zhu
In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.
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.
2 code implementations • 26 Aug 2020 • Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao, Jianbing Shen, Ce Zhu
Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.
Ranked #3 on RGB-D Salient Object Detection on STERE
1 code implementation • 26 Jul 2020 • Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, Zenglin Xu
Firstly, the embedded representations of multiple views are learned individually by deep autoencoders.
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 • 29 May 2020 • Yan Min, Mao Ye, Liang Tian, Yulin Jian, Ce Zhu, Shangming Yang
Our main contributions are a novel feature section approach which uses multi-step transition probability to characterize the data structure, and three algorithms proposed from the positive and negative aspects for keeping data structure.
no code implementations • 28 May 2020 • Chenpeng Zhang, Shuai Li, Mao Ye, Ce Zhu, Xue Li
Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences.
no code implementations • 28 May 2020 • Lihua Zhou, Mao Ye, Xinpeng Li, Ce Zhu, Yiguang Liu, Xue Li
By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly.
no code implementations • 16 May 2020 • Zhiyuan Zha, Xin Yuan, Joey Tianyi Zhou, Jiantao Zhou, Bihan Wen, Ce Zhu
In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors.
no code implementations • 6 May 2020 • Jing Wu, Xiang Zhang, Mingyi Zhou, Ce Zhu
Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance.
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 • 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.
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 • 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.
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.
6 code implementations • CVPR 2020 • Feng Zhang, Xiatian Zhu, Hanbin Dai, Mao Ye, Ce Zhu
Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.
Ranked #2 on Multi-Person Pose Estimation on MS COCO (using extra training data)
1 code implementation • CVPR 2019 • Chao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu
Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models.
Ranked #3 on Age Estimation on FGNET
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.
1 code implementation • 6 Jul 2018 • Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou, Jiachao Zhang, Ce Zhu
Towards this end, we first obtain a good reference of the original image groups by using the image NSS prior, and then the rank residual of the image groups between this reference and the degraded image is minimized to achieve a better estimate to the desired image.
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.
11 code implementations • CVPR 2018 • Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao
Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.
Ranked #10 on Language Modelling on Penn Treebank (Character Level)
no code implementations • 8 Feb 2018 • Shuai Li, Ce Zhu, Ming-Ting Sun
In this paper, we first examine the view interpolation with multiple reference views, demonstrating that the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views.
no code implementations • 12 Sep 2017 • Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou, Jiachao Zhang, Ce Zhu
Sparse coding has achieved a great success in various image processing tasks.
no code implementations • 16 Jun 2017 • Shuai Li, Wanqing Li, Chris Cook, Ce Zhu, Yanbo Gao
Such a network with learnable pooling function is referred to as a fully trainable network (FTN).
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.
no code implementations • 16 Aug 2016 • Zhiyuan Zha, Bihan Wen, Jiachao Zhang, Jiantao Zhou, Ce Zhu
Inspired by enhancing sparsity of the weighted L1-norm minimization in comparison with L1-norm minimization in sparse representation, we thus explain that WNNM is more effective than NMM.
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.