no code implementations • 24 Apr 2024 • Melih Yazgan, Thomas Graf, Min Liu, Tobias Fleck, J. Marius Zoellner
This survey analyzes intermediate fusion methods in collaborative perception for autonomous driving, categorized by real-world challenges.
no code implementations • 16 Apr 2024 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Tianliu He, Wen Wang
On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI inference without relying on remote servers.
no code implementations • 7 Apr 2024 • Zhiqiang Cai, Tong Ding, Min Liu, Xinyu Liu, Jianlin Xia
In this paper, we propose a structure-guided Gauss-Newton (SgGN) method for solving least squares problems using a shallow ReLU neural network.
no code implementations • 4 Apr 2024 • Qingxiang Liu, Sheng Sun, Yuxuan Liang, Jingjing Xue, Min Liu
From spatial perspective, we design lightweight-but-efficient prototypes as client-level semantic representations, based on which the server evaluates spatial similarity and yields client-customized global prototypes for the supplemented inter-client contrastive task.
2 code implementations • 1 Jan 2024 • Zhiyuan Wu, Tianliu He, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Xuefeng Jiang
Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data.
1 code implementation • 7 Dec 2023 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Tian Wen, Wen Wang
ALU drastically decreases the frequency of communication in federated distillation, thereby significantly reducing the communication overhead during the training process.
no code implementations • 6 Dec 2023 • Min Liu, Gang Yang, Siyuan Luo, Lin Shao
We present SoftMAC, a differentiable simulation framework that couples soft bodies with articulated rigid bodies and clothes.
1 code implementation • 1 Dec 2023 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Quyang Pan, Tianliu He, Xuefeng Jiang
Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy.
1 code implementation • 27 Nov 2023 • Xiang Chen, Min Liu, Rongguang Wang, Renjiu Hu, Dongdong Liu, Gaolei Li, Hang Zhang
Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts.
Ranked #2 on Image Registration on Unpaired-abdomen-CT (using extra training data)
no code implementations • 14 Nov 2023 • Yuwei Wang, Runhan Li, Hao Tan, Xuefeng Jiang, Sheng Sun, Min Liu, Bo Gao, Zhiyuan Wu
By fusing the logits of the two models, the private weak learner can capture the variance of different data, regardless of their category.
1 code implementation • ICCV 2023 • Min Liu, Alberto Sangiovanni-Vincentelli, Xiangyu Yue
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added.
no code implementations • 14 Jul 2023 • Jingjing Xue, Min Liu, Sheng Sun, Yuwei Wang, Hui Jiang, Xuefeng Jiang
In this paper, we propose Federated learning with Bayesian Inference-based Adaptive Dropout (FedBIAD), which regards weight rows of local models as probability distributions and adaptively drops partial weight rows based on importance indicators correlated with the trend of local training loss.
no code implementations • 31 Mar 2023 • Min Liu, Yu Bao, Chengqi Zhao, ShuJian Huang
Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks.
no code implementations • 17 Feb 2023 • Qingxiang Liu, Sheng Sun, Min Liu, Yuwei Wang, Bo Gao
In this paper, we perform the first study of forecasting traffic flow adopting Online Learning (OL) manner in FL framework and then propose a novel prediction method named Online Spatio-Temporal Correlation-based Federated Learning (FedOSTC), aiming to guarantee performance gains regardless of traffic fluctuation.
1 code implementation • 14 Jan 2023 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Xuefeng Jiang, Runhan Li, Bo Gao
The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine Learning (ML) models without sharing their private data.
no code implementations • 7 Jan 2023 • Demin Yu, Min Liu, Zhongjie Wang
Considering that traditional dialogue system with static slots cannot be directly applied to the SRE task, it is a challenge to design an efficient dialogue strategy to guide users to express their complete and accurate requirements in such a huge potential requirement space.
1 code implementation • 1 Jan 2023 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Quyang Pan, Xuefeng Jiang, Bo Gao
Federated Multi-task Learning (FMTL) is proposed to train related but personalized ML models for different devices, whereas previous works suffer from excessive communication overhead during training and neglect the model heterogeneity among devices in MEC.
no code implementations • 12 Oct 2022 • Yu Zheng, Jinghan Peng, Miao Zhao, Yufeng Ma, Min Liu, Xinyue Ma, Tianyu Liang, Tianlong Kong, Liang He, Minqiang Xu
This paper presents the system description of the THUEE team for the NIST 2020 Speaker Recognition Evaluation (SRE) conversational telephone speech (CTS) challenge.
no code implementations • 23 Sep 2022 • Yu Zheng, Jinghan Peng, Yihao Chen, Yajun Zhang, Jialong Wang, Min Liu, Minqiang Xu
In the pre-training stage we reserve the speaker weights, and there are no positive samples to train them in this stage.
no code implementations • 22 Sep 2022 • Yu Zheng, Yihao Chen, Jinghan Peng, Yajun Zhang, Min Liu, Minqiang Xu
In the SV task fixed track, our system was a fusion of five models, and two models were fused in the SV task open track.
no code implementations • 18 Sep 2022 • Min Liu, Siwen Jin, Luo Jin, Shuohan Wang, Yu Fang, Yuliang Shi
Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task.
1 code implementation • 25 Aug 2022 • Xuefeng Jiang, Sheng Sun, Yuwei Wang, Min Liu
Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner.
no code implementations • 23 Jul 2022 • Tianle Ni, Jingwei Wang, Yunlong Ma, Shuang Wang, Min Liu, Weiming Shen
Here, we present a careful theoretical and empirical analysis of the ATDC algorithm, showing that the calculation of anomaly scores in both stages can be simplified, and that the second stage of the algorithm is much more important than the first stage.
no code implementations • 17 May 2022 • Yuhao Mo, Chu Han, Yu Liu, Min Liu, Zhenwei Shi, Jiatai Lin, Bingchao Zhao, Chunwang Huang, Bingjiang Qiu, Yanfen Cui, Lei Wu, Xipeng Pan, Zeyan Xu, Xiaomei Huang, Zaiyi Liu, Ying Wang, Changhong Liang
In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.
no code implementations • 12 May 2022 • Rina Friedberg, Karthik Rajkumar, Jialiang Mao, Qian Yao, YinYin Yu, Min Liu
By leveraging prior experimentation, we obtain quasi-experimental variation in item rankings that is orthogonal to user relevance.
2 code implementations • 14 Apr 2022 • Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Quyang Pan, Junbo Zhang, Zeju Li, Qingxiang Liu
Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead.
no code implementations • 3 Apr 2022 • Qijin She, Ruizhen Hu, Juzhan Xu, Min Liu, Kai Xu, Hui Huang
To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object.
no code implementations • 25 Feb 2022 • Yuan Gao, Kaiyu Yang, Yuanlong Chen, Min Liu, Noureddine El Karoui
We establish a general optimization framework for the design of automated bidding agent in dynamic online marketplaces.
no code implementations • 27 Jan 2022 • Chunyong Yang, PengFei Liu, Yanli Chen, Hongbin Wang, Min Liu
The end to end TTS system is VITS, and the pre-training self-supervised model is wav2vec 2. 0.
no code implementations • 29 Nov 2021 • Yuling Jiao, Dingwei Li, Min Liu, Xiangliang Lu, Yuanyuan Yang
In this paper, we consider recovering $n$ dimensional signals from $m$ binary measurements corrupted by noises and sign flips under the assumption that the target signals have low generative intrinsic dimension, i. e., the target signals can be approximately generated via an $L$-Lipschitz generator $G: \mathbb{R}^k\rightarrow\mathbb{R}^{n}, k\ll n$.
no code implementations • 21 Oct 2021 • Zhiqiang Cai, Jingshuang Chen, Min Liu
A least-squares neural network (LSNN) method was introduced for solving scalar linear and nonlinear hyperbolic conservation laws (HCLs) in [7, 6].
no code implementations • 10 Oct 2021 • Yufeng Ma, Yiwei Ding, Miao Zhao, Yu Zheng, Min Liu, Minqiang Xu
Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network.
no code implementations • 8 Oct 2021 • Xin Zhong, Chen Chen, Shu Fu, Zhihong Zeng, Min Liu
Generalized optical multiple-input multiple-output (GOMIMO) techniques have been recently shown to be promising for high-speed optical wireless communication (OWC) systems.
no code implementations • 29 Sep 2021 • Min Liu, Zhiqiang Cai, Karthik Ramani
This paper presents RitzNet, an unsupervised learning method which takes any point in the computation domain as input, and learns a neural network model to output its corresponding function value satisfying the underlying governing PDEs.
no code implementations • 18 Sep 2021 • Yuling Jiao, Dingwei Li, Min Liu, Xiliang Lu
Recovering sparse signals from observed data is an important topic in signal/imaging processing, statistics and machine learning.
no code implementations • 7 Sep 2021 • Zhiqiang Cai, Jingshuang Chen, Min Liu
Designing an optimal deep neural network for a given task is important and challenging in many machine learning applications.
no code implementations • ICCV 2021 • Xueping Wang, Shasha Li, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury
The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID).
no code implementations • 24 Jun 2021 • Chen Chen, Lin Zeng, Xin Zhong, Shu Fu, Min Liu, Pengfei Du
In this paper, we propose an orthogonal frequency division multiplexing (OFDM)-based generalized optical quadrature spatial modulation (GOQSM) technique for multiple-input multiple-output optical wireless communication (MIMO-OWC) systems.
no code implementations • 9 Jun 2021 • Baoyun Peng, Min Liu, Zhaoning Zhang, Kai Xu, Dongsheng Li
Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
no code implementations • 25 May 2021 • Zhiqiang Cai, Jingshuang Chen, Min Liu
We introduced the least-squares ReLU neural network (LSNN) method for solving the linear advection-reaction problem with discontinuous solution and showed that the method outperforms mesh-based numerical methods in terms of the number of degrees of freedom.
no code implementations • 25 May 2021 • Zhiqiang Cai, Jingshuang Chen, Min Liu
This paper studies least-squares ReLU neural network method for solving the linear advection-reaction problem with discontinuous solution.
no code implementations • 3 Sep 2020 • Junrui Tian, Zhiying Tu, Zhongjie Wang, Xiaofei Xu, Min Liu
In recent years, chat-bot has become a new type of intelligent terminal to guide users to consume services.
no code implementations • 21 Jul 2020 • Xueping Wang, Sujoy Paul, Dripta S. Raychaudhuri, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury, Fellow, IEEE
In order to cope with this issue, we introduce the problem of learning person re-identification models from videos with weak supervision.
Multiple Instance Learning Video-Based Person Re-Identification
no code implementations • 20 May 2020 • Chen Chen, Shu Fu, Xin Jian, Min Liu, Xiong Deng, Zhiguo Ding
In order to improve the energy efficiency (EE) of the bidirectional LiFi-IoT system, non-orthogonal multiple access (NOMA) with a quality-of-service (QoS)-guaranteed optimal power allocation (OPA) strategy is applied to maximize the EE of the system.
no code implementations • 4 Feb 2020 • Min Liu, Zherong Pan, Kai Xu, Kanishka Ganguly, Dinesh Manocha
We present an end-to-end algorithm for training deep neural networks to grasp novel objects.
Robotics
1 code implementation • 5 Nov 2019 • Zhiqiang Cai, Jingshuang Chen, Min Liu, Xinyu Liu
This paper studies an unsupervised deep learning-based numerical approach for solving partial differential equations (PDEs).
no code implementations • 27 Aug 2019 • Xueping Wang, Rameswar Panda, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury
Additionally, a cross-view matching strategy followed by global camera network constraints is proposed to explore the matching relationships across the entire camera network.
no code implementations • 28 Jul 2019 • Zongyue Zhao, Min Liu, Karthik Ramani
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis.
no code implementations • ICLR 2019 • Min Liu, Fupin Yao, Chiho Choi, Sinha Ayan, Karthik Ramani
The ground-breaking performance obtained by deep convolutional neural networks (CNNs) for image processing tasks is inspiring research efforts attempting to extend it for 3D geometric tasks.
no code implementations • 1 Mar 2019 • Min Liu, Zherong Pan, Kai Xu, Kanishka Ganguly, Dinesh Manocha
The quality of the grasp poses is on par with the groundtruth poses in the dataset.
Robotics
no code implementations • 30 Aug 2018 • Mohan Li, Min Liu, Masanori Hattori
In this paper, we present Adaptive Computation Steps (ACS) algo-rithm, which enables end-to-end speech recognition models to dy-namically decide how many frames should be processed to predict a linguistic output.
Ranked #13 on Speech Recognition on AISHELL-1
no code implementations • 10 May 2018 • Min Liu, Tobi Delbruck
The precise event timing, sparse output, and wide dynamic range of the events are well suited for optical flow, but conventional optical flow (OF) algorithms are not well matched to the event stream data.
no code implementations • 16 Jun 2017 • Min Liu, Tobi Delbruck
Rapid and low power computation of optical flow (OF) is potentially useful in robotics.
no code implementations • 14 Oct 2016 • Min Liu, Yifei Shi, Lintao Zheng, Kai Xu, Hui Huang, Dinesh Manocha
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed.