no code implementations • 31 May 2023 • Dingcheng Luo, Thomas O'Leary-Roseberry, Peng Chen, Omar Ghattas
We propose a novel machine learning framework for solving optimization problems governed by large-scale partial differential equations (PDEs) with high-dimensional random parameters.
no code implementations • 21 May 2023 • Qian Huang, Hongyu Ren, Peng Chen, Gregor Kržmanc, Daniel Zeng, Percy Liang, Jure Leskovec
In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters.
no code implementations • 27 Apr 2023 • Bowen Wang, Jianchi Zhu, Xiaoming She, Peng Chen
The orthogonal time frequency space (OTFS) modulation as a promising signal representation attracts growingcinterest for integrated sensing and communication (ISAC), yet its merits over orthogonal frequency division multiplexing (OFDM) remain controversial.
no code implementations • 22 Apr 2023 • Peng Chen, Xin Du, Zhihui Lu, Hongfeng Chai
To this end, we define a threat model for backdoor attacks in VFL and introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL.
no code implementations • 20 Apr 2023 • Tang Tao, Longfei Gao, Guangrun Wang, Peng Chen, Dayang Hao, Xiaodan Liang, Mathieu Salzmann, Kaicheng Yu
To evaluate the effectiveness of our approach, we establish an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL.
no code implementations • 20 Mar 2023 • Haohao Sun, Yilong Zhang, Peng Chen, Haixia Wang, Ronghua Liang
As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications.
1 code implementation • CVPR 2023 • Lei Yang, Kaicheng Yu, Tao Tang, Jun Li, Kun Yuan, Li Wang, Xinyu Zhang, Peng Chen
In essence, instead of predicting the pixel-wise depth, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods.
Ranked #1 on 3D Object Detection on DAIR-V2X-I
no code implementations • 13 Mar 2023 • Sixiang Chen, Tian Ye, Jun Shi, Yun Liu, Jingxia Jiang, ErKang Chen, Peng Chen
Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges.
no code implementations • 21 Feb 2023 • Binwei Xu, Haoran Liang, Weihua Gong, Ronghua Liang, Peng Chen
Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels.
no code implementations • 7 Dec 2022 • Yinpeng Dong, Peng Chen, Senyou Deng, Lianji L, Yi Sun, Hanyu Zhao, Jiaxing Li, Yunteng Tan, Xinyu Liu, Yangyi Dong, Enhui Xu, Jincai Xu, Shu Xu, Xuelin Fu, Changfeng Sun, Haoliang Han, Xuchong Zhang, Shen Chen, Zhimin Sun, Junyi Cao, Taiping Yao, Shouhong Ding, Yu Wu, Jian Lin, Tianpeng Wu, Ye Wang, Yu Fu, Lin Feng, Kangkang Gao, Zeyu Liu, Yuanzhe Pang, Chengqi Duan, Huipeng Zhou, Yajie Wang, Yuhang Zhao, Shangbo Wu, Haoran Lyu, Zhiyu Lin, YiFei Gao, Shuang Li, Haonan Wang, Jitao Sang, Chen Ma, Junhao Zheng, Yijia Li, Chao Shen, Chenhao Lin, Zhichao Cui, Guoshuai Liu, Huafeng Shi, Kun Hu, Mengxin Zhang
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
no code implementations • 4 Dec 2022 • Binwei Xu, Haoran Liang, Ronghua Liang, Peng Chen
BAB aims to help predict accurate boundaries, whose input is the synthetic image.
no code implementations • 18 Nov 2022 • Bicheng Guo, Shuxuan Guo, Miaojing Shi, Peng Chen, Shibo He, Jiming Chen, Kaicheng Yu
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
no code implementations • 15 Nov 2022 • Zihan Yang, Peng Chen, Ziyu Guo, Dahai Ni
In this work, we consider the Direction-of-Arrival (DOA) estimation problem in a low-cost architecture where only one antenna as the receiver is aided by a reconfigurable intelligent surface (RIS).
no code implementations • 2 Nov 2022 • Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Feigege Wang, Peng Chen
Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images.
1 code implementation • 5 Oct 2022 • Tao Luo, Peng Chen, Zhenxin Cao, Le Zheng, Zongxin Wang
The computational complexity of the conventional adaptive beamformer is relatively large, and the performance degrades significantly due to the model mismatch errors and the unwanted signals in received data.
no code implementations • 12 Jul 2022 • Sixiang Chen, Tian Ye, Yun Liu, Taodong Liao, Jingxia Jiang, ErKang Chen, Peng Chen
Snow removal causes challenges due to its characteristic of complex degradations.
1 code implementation • 21 Jun 2022 • Thomas O'Leary-Roseberry, Peng Chen, Umberto Villa, Omar Ghattas
We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to output function spaces or quantities of interest.
1 code implementation • 26 May 2022 • Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li
We study the variational problem in the family of two-layer networks with squared-ReLU activations, towards which we derive a semi-definite programming (SDP) relaxation.
1 code implementation • 25 May 2022 • Peng Chen, Zhimin Chen, Pu Miao, Yun Chen
The reconfigurable intelligent surface (RIS) has been a potential technology for future radar and wireless communication applications.
1 code implementation • 18 May 2022 • Liang Liu, Peng Chen, Guangchun Luo, Zhao Kang, Yonggang Luo, Sanchu Han
With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years.
no code implementations • 12 May 2022 • Xiao Wang, Aristeidis Tsaris, Debangshu Mukherjee, Mohamed Wahib, Peng Chen, Mark Oxley, Olga Ovchinnikova, Jacob Hinkle
In this paper, we propose a novel image gradient decomposition method that significantly reduces the memory footprint for ptychographic reconstruction by tessellating image gradients and diffraction measurements into tiles.
1 code implementation • 25 Apr 2022 • Zhimin Chen, Peng Chen, Ziyu Guo, Yudong Zhang, Xianbin Wang
A novel atomic norm-based method is proposed to remove the interference signals by sparse reconstruction, which can improve the DOA estimation efficiently.
1 code implementation • 5 Apr 2022 • Binwei Xu, Haoran Liang, Wentian Ni, Weihua Gong, Ronghua Liang, Peng Chen
Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, weak annotations, or part of the pixel-wise annotations.
no code implementations • 19 Mar 2022 • Peng Chen, Zihan Yang, Zhimin Chen, Ziyu Guo
The direction of arrival (DOA) estimation problem is addressed in this letter.
1 code implementation • 19 Mar 2022 • Peng Chen, Zhimin Chen, Beixiong Zheng, Xianbin Wang
Specifically, considering the position perturbation of UAVs, a new atomic norm-based DOA estimation method is proposed, where an atomic norm is defined with the parameter of the position perturbation.
1 code implementation • 19 Mar 2022 • Peng Chen, Zhimin Chen, Liang Liu, Yun Chen, Xianbin Wang
Simulation results show that the proposed SDOAnet outperforms the existing DOA estimation methods with the effect of the imperfect array.
3 code implementations • 22 Nov 2021 • Zizheng Pan, Peng Chen, Haoyu He, Jing Liu, Jianfei Cai, Bohan Zhuang
While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all intermediate activations that are needed for gradient computation during backpropagation, especially for long sequences.
no code implementations • 14 Oct 2021 • Igor L. Markov, Hanson Wang, Nitya Kasturi, Shaun Singh, Sze Wai Yuen, Mia Garrard, Sarah Tran, Yin Huang, Zehui Wang, Igor Glotov, Tanvi Gupta, Boshuang Huang, Peng Chen, Xiaowen Xie, Michael Belkin, Sal Uryasev, Sam Howie, Eytan Bakshy, Norm Zhou
Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems.
1 code implementation • 12 Sep 2021 • Tian Ye, ErKang Chen, XinRui Huang, Peng Chen
This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image.
1 code implementation • EMNLP 2021 • Peng Chen
Based on the analysis, we propose PermuteFormer, a Performer-based model with relative position encoding that scales linearly on long sequences.
no code implementations • 30 Jul 2021 • Xiangyun Li, Peng Chen, Zhanpeng Bao
The electroencephalography (EEG) signal is a non-stationary, stochastic, and highly non-linear bioelectric signal for which achieving high classification accuracy is challenging, especially when the number of subjects is limited.
1 code implementation • 18 Jun 2021 • Peng Chen, Liang Liu, Zhengrui Ma, Zhao Kang
In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views.
1 code implementation • 8 May 2021 • Yuliang Liu, Chunhua Shen, Lianwen Jin, Tong He, Peng Chen, Chongyu Liu, Hao Chen
Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output.
no code implementations • 7 Apr 2021 • Jin Liu, Peng Chen, Tao Liang, Zhaoxing Li, Cai Yu, Shuqiao Zou, Jiao Dai, Jizhong Han
Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously.
1 code implementation • 12 Feb 2021 • Yifei Wang, Peng Chen, Wuchen Li
We propose a projected Wasserstein gradient descent method (pWGD) for high-dimensional Bayesian inference problems.
1 code implementation • 12 Feb 2021 • Keyi Wu, Peng Chen, Omar Ghattas
Optimal experimental design (OED) plays an important role in the problem of identifying uncertainty with limited experimental data.
Optimization and Control Numerical Analysis Numerical Analysis
no code implementations • 29 Jan 2021 • Peng Chen, Gui-Jun Ding, Stephen F. King
We combine $SU(5)$ Grand Unified Theories (GUTs) with $A_4$ modular symmetry and present a comprehensive analysis of the resulting quark and lepton mass matrices for all the simplest cases.
High Energy Physics - Phenomenology
no code implementations • 13 Jan 2021 • Jing Liu, Bohan Zhuang, Peng Chen, Chunhua Shen, Jianfei Cai, Mingkui Tan
By jointly training the binary gates in conjunction with network parameters, the compression configurations of each layer can be automatically determined.
no code implementations • ICLR 2021 • Zhen Han, Peng Chen, Yunpu Ma, Volker Tresp
We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task.
1 code implementation • 31 Dec 2020 • Zhen Han, Peng Chen, Yunpu Ma, Volker Tresp
We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task.
1 code implementation • 30 Nov 2020 • Thomas O'Leary-Roseberry, Umberto Villa, Peng Chen, Omar Ghattas
We use the projection basis vectors in the active subspace as well as the principal output subspace to construct the weights for the first and last layers of the neural network, respectively.
1 code implementation • 29 Nov 2020 • Hu Wang, Peng Chen, Bohan Zhuang, Chunhua Shen
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods.
1 code implementation • EMNLP 2020 • Zhen Han, Yunpu Ma, Peng Chen, Volker Tresp
Product manifolds enable our approach to better reflect a wide variety of geometric structures on temporal KGs.
no code implementations • 16 Sep 2020 • Martin Kuo, Yaobo Liang, Lei Ji, Nan Duan, Linjun Shou, Ming Gong, Peng Chen
The semi-structured answer has two advantages which are more readable and falsifiable compared to span answer.
no code implementations • ICCV 2021 • Peng Chen, Bohan Zhuang, Chunhua Shen
Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts.
no code implementations • CVPR 2021 • Peng Chen, Jing Liu, Bohan Zhuang, Mingkui Tan, Chunhua Shen
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.
no code implementations • 3 May 2020 • Weifeng Han, Peng Chen, Zhenxin Cao
In this letter, a direction of angle (DOA) estimation problem is investigated with low-cost ADC in IRS, and we propose a deep neural network (DNN) as a recovery method for the low-resolution sampled signal.
no code implementations • 5 Mar 2020 • Peng Chen, Gui-Jun Ding, Jun-Nan Lu, José W. F. Valle
We propose a realistic theory of fermion masses and mixings using a five-dimensional warped scenario where all fermions propagate in the bulk and the Higgs field is localized on the IR brane.
High Energy Physics - Phenomenology
1 code implementation • Proceedings of the IEEE Winter Conference on Applications of Computer Vision Workshops 2020 • Wenhe Liu, Guoliang Kang, Po-Yao Huang, Xiaojun Chang, Yijun Qian, Junwei Liang, Liangke Gui, Jing Wen, Peng Chen
We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario.
1 code implementation • 14 Feb 2020 • Nick Alger, Peng Chen, Omar Ghattas
We present a method for converting tensors into tensor train format based on actions of the tensor as a vector-valued multilinear function.
Numerical Analysis Numerical Analysis
1 code implementation • NeurIPS 2020 • Peng Chen, Omar Ghattas
The curse of dimensionality is a longstanding challenge in Bayesian inference in high dimensions.
no code implementations • 1 Feb 2020 • Lijun Yu, Peng Chen, Wenhe Liu, Guoliang Kang, Alexander G. Hauptmann
To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance.
no code implementations • 26 Jan 2020 • Xiao Wang, Robert D. MacDougall, Peng Chen, Charles A. Bouman, Simon K. Warfield
Our algorithm uses precise physics models to reconstruct from the native cone-beam geometry and interleaved dual source helical trajectory of a DS-FFS CT. To do so, we construct a noise physics model to represent data acquisition noise and a prior image model to represent image noise and texture.
no code implementations • 24 Dec 2019 • WeiRan Yan, MaoLin Tang, Qijun Zhao, Peng Chen, Dunwu Qi, Rong Hou, Zhihe Zhang
Giant pandas, stereotyped as silent animals, make significantly more vocal sounds during breeding season, suggesting that sounds are essential for coordinating their reproduction and expression of mating preference.
no code implementations • 23 Dec 2019 • Chong Huang, Yuanjie Dang, Peng Chen, Xin Yang, Kwang-Ting, Cheng
Imitation learning has been applied to mimic the operation of a human cameraman in several autonomous cinematography systems.
1 code implementation • NeurIPS 2019 • Peng Chen, Keyi Wu, Joshua Chen, Tom O'Leary-Roseberry, Omar Ghattas
We propose a projected Stein variational Newton (pSVN) method for high-dimensional Bayesian inference.
no code implementations • 5 Nov 2019 • Philip Sperl, Ching-Yu Kao, Peng Chen, Konstantin Böttinger
In this paper, we present a novel end-to-end framework to detect such attacks during classification without influencing the target model's performance.
no code implementations • 5 Oct 2019 • Peng Chen, Zhimin Chen, Zhenxin Cao, Xianbin Wang
The problem of direction of arrival (DOA) estimation has been studied for decades as an essential technology in enabling radar, wireless communications, and array signal processing related applications.
no code implementations • 22 Sep 2019 • Bohan Zhuang, Chunhua Shen, Mingkui Tan, Peng Chen, Lingqiao Liu, Ian Reid
Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature.
no code implementations • 16 Aug 2019 • Peng Chen, Tong Jia, Pengfei Wu, Jianjun Wu, Dongyue Chen
Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods.
no code implementations • 9 Aug 2019 • Qi He, Qijun Zhao, Ning Liu, Peng Chen, Zhihe Zhang, Rong Hou
We are going to release our database and model in the public domain to promote the research on automatic animal identification and particularly on the technique for protecting red pandas.
no code implementations • ACL 2019 • Pengcheng Yang, Fuli Luo, Peng Chen, Tianyu Liu, Xu sun
The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages.
no code implementations • ACL 2019 • Botian Shi, Lei Ji, Yaobo Liang, Nan Duan, Peng Chen, Zhendong Niu, Ming Zhou
Understanding narrated instructional videos is important for both research and real-world web applications.
no code implementations • 29 May 2019 • Peng Chen, Jianzhong Liu, Hao Chen
Our evaluation also uncovered the key technique contributing to Matryoshka's impressive performance: it collects only the nesting constraints that may cause the target conditional statements unreachable, which greatly simplifies the constraints that it has to solve.
Cryptography and Security
no code implementations • 27 May 2019 • Wojciech Michal Matkowski, Adams Wai Kin Kong, Han Su, Peng Chen, Rong Hou, Zhihe Zhang
Cameras have been widely installed in the regions where pandas live.
1 code implementation • IJCAI 2019 2019 • Pengcheng Yang, Fuli Luo, Peng Chen, Lei LI, Zhiyi Yin, Xiaodong He, Xu sun
The visual storytelling (VST) task aims at generating a reasonable and coherent paragraph-level story with the image stream as input.
1 code implementation • 22 Jan 2019 • Fan Meng, Peng Chen, Lenan Wu, Julian Cheng
The model-based power allocation algorithm has been investigated for decades, but it requires the mathematical models to be analytically tractable and it usually has high computational complexity.
Information Theory Information Theory
2 code implementations • 7 Dec 2018 • Fan Meng, Peng Chen, Lenan Wu
Nowadays, the data-driven model-free machine learning-based approaches are rapidly developed in this field, and among them the deep reinforcement learning (DRL) is proved to be of great promising potential.
Information Theory Information Theory
no code implementations • 23 Aug 2018 • Zhirui Zhang, Shuo Ren, Shujie Liu, Jianyong Wang, Peng Chen, Mu Li, Ming Zhou, Enhong Chen
Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content.
Ranked #3 on Unsupervised Text Style Transfer on GYAFC
no code implementations • EMNLP 2018 • Daya Guo, Yibo Sun, Duyu Tang, Nan Duan, Jian Yin, Hong Chi, James Cao, Peng Chen, Ming Zhou
We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data.
no code implementations • 12 Apr 2018 • Peng Chen, Zhenxin Cao, Zhimin Chen, Xianbin Wang
With regard to the DOA estimation performance, the proposed SBLMC method can outperform state-of-the-art methods in the MIMO radar with unknown mutual coupling effect, while keeping the acceptable computational complexity.
2 code implementations • 4 Mar 2018 • Peng Chen, Hao Chen
On the LAVA-M data set, Angora found almost all the injected bugs, found more bugs than any other fuzzer that we compared with, and found eight times as many bugs as the second-best fuzzer in the program who.
Cryptography and Security
no code implementations • EMNLP 2017 • Nan Duan, Duyu Tang, Peng Chen, Ming Zhou
This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data.
2 code implementations • EMNLP 2017 • Peng Chen, Zhongqian Sun, Lidong Bing, Wei Yang
We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review.