no code implementations • 8 Jan 2024 • Wencheng Han, Dongqian Guo, Cheng-Zhong Xu, Jianbing Shen
On the other hand, the generation of accurate control signals relies on precise and detailed environmental perception, which is where 3D scene perception models excel.
1 code implementation • 29 Dec 2023 • Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, Cheng-Zhong Xu
We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes.
1 code implementation • 25 Dec 2023 • Li Xiang, Junbo Yin, Wei Li, Cheng-Zhong Xu, Ruigang Yang, Jianbing Shen
Specifically, DMA builds a domain-mixing 3D instance bank for the teacher and student models during training, resulting in aligned data representation.
1 code implementation • 7 Aug 2023 • Tianrui Qin, Xitong Gao, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu
To further evaluate the attack and defense capabilities of these poisoning methods, we have developed a benchmark -- APBench for assessing the efficacy of adversarial poisoning.
1 code implementation • 13 May 2023 • Tian Gao, Cheng-Zhong Xu, Le Zhang, Hui Kong
Compared with the full-precision one, the model with the binarization method replaces complex tensor multiplication with simple bit-wise binary operations and represents full-precision model parameters and activations with only 1-bit ones, which potentially solves the problem of model size and computational complexity, respectively.
1 code implementation • 27 Mar 2023 • Tianrui Qin, Xitong Gao, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu
In this paper, we introduce the UEraser method, which outperforms current defenses against different types of state-of-the-art unlearnable example attacks through a combination of effective data augmentation policies and loss-maximizing adversarial augmentations.
no code implementations • CVPR 2023 • Runzhou Tao, Wencheng Han, Zhongying Qiu, Cheng-Zhong Xu, Jianbing Shen
When used as a pre-training method, our model can significantly outperform the corresponding fully-supervised baseline with only 1/3 3D labels.
1 code implementation • 29 Jan 2023 • Jin Fang, Dingfu Zhou, Jingjing Zhao, Chenming Wu, Chulin Tang, Cheng-Zhong Xu, Liangjun Zhang
This setting results in two distinct domain gaps: scenarios and sensors, making it difficult to analyze and evaluate the method accurately.
no code implementations • ICCV 2023 • Xinquan Chen, Xitong Gao, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu
It can generate UAEs from scratch or conditionally based on reference images.
no code implementations • CVPR 2023 • Yunrui Yu, Cheng-Zhong Xu
Attackers can deceive neural networks by adding human imperceptive perturbations to their input data; this reveals the vulnerability and weak robustness of current deep-learning networks.
1 code implementation • 20 Dec 2022 • Tianrui Qin, Xianghuan He, Xitong Gao, Yiren Zhao, Kejiang Ye, Cheng-Zhong Xu
Open software supply chain attacks, once successful, can exact heavy costs in mission-critical applications.
1 code implementation • 15 Nov 2022 • Yunrui Yu, Xitong Gao, Cheng-Zhong Xu
In particular, most ensemble defenses exhibit near or exactly 0% robustness against MORA with $\ell^\infty$ perturbation within 0. 02 on CIFAR-10, and 0. 01 on CIFAR-100.
1 code implementation • 26 Jul 2022 • Junbo Yin, Jin Fang, Dingfu Zhou, Liangjun Zhang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang
To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed.
1 code implementation • 26 Jul 2022 • Junbo Yin, Dingfu Zhou, Liangjun Zhang, Jin Fang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination.
no code implementations • 12 Jun 2022 • Hang Hua, Xingjian Li, Dejing Dou, Cheng-Zhong Xu, Jiebo Luo
The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing.
no code implementations • 30 Apr 2022 • Yubin Guo, Haobo Jiang, Xinlei Qi, Jin Xie, Cheng-Zhong Xu, Hui Kong
Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society.
1 code implementation • CVPR 2022 • Liang Gao, Huazhu Fu, Li Li, YingWen Chen, Ming Xu, Cheng-Zhong Xu
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data.
no code implementations • 14 Mar 2022 • Hou Pong Chan, Mingxi Guo, Cheng-Zhong Xu
In this work, we study the problem of language grounding for autonomous vehicles, which aims to localize a region in a visual scene according to a natural language command from a passenger.
1 code implementation • 10 Dec 2021 • Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu
In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.
no code implementations • 24 Oct 2021 • Kafeng Wang, Haoyi Xiong, Jie Zhang, Hongyang Chen, Dejing Dou, Cheng-Zhong Xu
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
no code implementations • 29 Sep 2021 • Dongping Liao, Xitong Gao, Yiren Zhao, Hao Dai, Li Li, Kafeng Wang, Kejiang Ye, Yang Wang, Cheng-Zhong Xu
Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.
no code implementations • NAACL 2021 • Hang Hua, Xingjian Li, Dejing Dou, Cheng-Zhong Xu, Jiebo Luo
The brittleness of this process is often reflected by the sensitivity to random seeds.
no code implementations • 20 Apr 2021 • Zhenning Li, Hao Yu, Guohui Zhang, Shangjia Dong, Cheng-Zhong Xu
Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • CVPR 2021 • Yunrui Yu, Xitong Gao, Cheng-Zhong Xu
In this paper, we show that latent features in certain "robust" models are surprisingly susceptible to adversarial attacks.
1 code implementation • CVPR 2021 • Abulikemu Abuduweili, Xingjian Li, Humphrey Shi, Cheng-Zhong Xu, Dejing Dou
To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples.
no code implementations • 16 Oct 2020 • Boyi Liu, Lujia Wang, Xinquan Chen, Lexiong Huang, Cheng-Zhong Xu
Both data and models are shared by robots to the cloud after semantic computing and training locally.
no code implementations • 8 Sep 2020 • Boyi Liu, Bingjie Yan, Yize Zhou, Zhixuan Liang, Cheng-Zhong Xu
Furthermore, we developed federated learning open-source software based on FedCM.
1 code implementation • 7 Sep 2020 • Zezhou Sun, Banghe Wu, Cheng-Zhong Xu, Sanjay E. Sarma, Jian Yang, Hui Kong
We propose an integrated approach to active exploration by exploiting the Cartographer method as the base SLAM module for submap creation and performing efficient frontier detection in the geometrically co-aligned submaps induced by graph optimization.
no code implementations • 20 Jul 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou
While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.
1 code implementation • ICML 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu, Dejing Dou
RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.
no code implementations • 24 May 2020 • Jiexia Ye, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu
Recently, various novel deep learning techniques have been developed to process graph data, called graph neural networks (GNNs).
1 code implementation • 11 May 2020 • Jiexia Ye, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu
However, it is well known that an individual stock price is correlated with prices of other stocks in complex ways.
no code implementations • ICLR 2020 • Kafeng Wang, Xitong Gao, Yiren Zhao, Xingjian Li, Dejing Dou, Cheng-Zhong Xu
Deep convolutional neural networks are now widely deployed in vision applications, but a limited size of training data can restrict their task performance.
no code implementations • 24 Dec 2019 • Boyi Liu, Lujia Wang, Ming Liu, Cheng-Zhong Xu
Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems.
no code implementations • 9 Dec 2019 • Ying Wang, Zezhou Sun, Cheng-Zhong Xu, Sanjay Sarma, Jian Yang, Hui Kong
In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection.
no code implementations • 2 Dec 2019 • Dong Han, Zuhao Zou, Lujia Wang, Cheng-Zhong Xu
Different from the conventional visual localization system, we design a novel visual optimization model by matching planar information between the LiDAR map and visual image.
no code implementations • 21 Oct 2019 • Yiren Zhao, Xitong Gao, Xuan Guo, Junyi Liu, Erwei Wang, Robert Mullins, Peter Y. K. Cheung, George Constantinides, Cheng-Zhong Xu
Furthermore, we show how Tomato produces implementations of networks with various sizes running on single or multiple FPGAs.
no code implementations • 3 Sep 2019 • Boyi Liu, Lujia Wang, Ming Liu, Cheng-Zhong Xu
The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems.
1 code implementation • NeurIPS 2019 • Yiren Zhao, Xitong Gao, Daniel Bates, Robert Mullins, Cheng-Zhong Xu
In ResNet-50, we achieved a 18. 08x CR with only 0. 24% loss in top-5 accuracy, outperforming existing compression methods.
no code implementations • 23 Jan 2019 • Ilia Shumailov, Xitong Gao, Yiren Zhao, Robert Mullins, Ross Anderson, Cheng-Zhong Xu
Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision.
2 code implementations • ICLR 2019 • Xitong Gao, Yiren Zhao, Łukasz Dudziak, Robert Mullins, Cheng-Zhong Xu
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources.
no code implementations • 19 Apr 2016 • Juanjuan Zhao, Fan Zhang, Lai Tu, Cheng-Zhong Xu, Dayong Shen, Chen Tian, Xiang-Yang Li, Zhengxi Li
Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities.