no code implementations • 2 May 2024 • Haicheng Liao, Zhenning Li, Chengyue Wang, Huanming Shen, Bonan Wang, Dongping Liao, Guofa Li, Chengzhong Xu
This paper introduces a trajectory prediction model tailored for autonomous driving, focusing on capturing complex interactions in dynamic traffic scenarios without reliance on high-definition maps.
no code implementations • 30 Apr 2024 • Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, Chengzhong Xu
Through a series of experiments, we have uncovered two critical insights that shed light on the training and parameter inefficiency of LoRA.
no code implementations • 20 Apr 2024 • Yebo Wu, Li Li, Chunlin Tian, Chengzhong Xu
In order to preserve the feature representation of each block, we decouple the whole training process into two stages: progressive model shrinking and progressive model growing.
no code implementations • 16 Apr 2024 • Xibin Jin, Guoliang Li, Shuai Wang, Miaowen Wen, Chengzhong Xu, H. Vincent Poor
Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals.
no code implementations • 11 Mar 2024 • Ruihua Han, Shuai Wang, Shuaijun Wang, Zeqing Zhang, Jianjun Chen, ShiJie Lin, Chengyang Li, Chengzhong Xu, Yonina C. Eldar, Qi Hao, Jia Pan
Navigating a nonholonomic robot in a cluttered environment requires extremely accurate perception and locomotion for collision avoidance.
no code implementations • 5 Mar 2024 • Yanchen Guan, Haicheng Liao, Zhenning Li, Guohui Zhang, Chengzhong Xu
In the rapidly evolving landscape of autonomous driving, the capability to accurately predict future events and assess their implications is paramount for both safety and efficiency, critically aiding the decision-making process.
1 code implementation • 29 Feb 2024 • Haicheng Liao, Yongkang Li, Zhenning Li, Chengyue Wang, Zhiyong Cui, Shengbo Eben Li, Chengzhong Xu
In autonomous vehicle (AV) technology, the ability to accurately predict the movements of surrounding vehicles is paramount for ensuring safety and operational efficiency.
1 code implementation • 11 Dec 2023 • Haicheng Liao, Zhenning Li, Huanming Shen, Wenxuan Zeng, Dongping Liao, Guofa Li, Shengbo Eben Li, Chengzhong Xu
The ability to accurately predict the trajectory of surrounding vehicles is a critical hurdle to overcome on the journey to fully autonomous vehicles.
1 code implementation • 6 Dec 2023 • Haicheng Liao, Huanming Shen, Zhenning Li, Chengyue Wang, Guofa Li, Yiming Bie, Chengzhong Xu
In the field of autonomous vehicles (AVs), accurately discerning commander intent and executing linguistic commands within a visual context presents a significant challenge.
no code implementations • 19 Nov 2023 • Jiashu Wu, Hao Dai, Kenneth B. Kent, Jerome Yen, Chengzhong Xu, Yang Wang
The OSDN model performs intrusion knowledge transfer from the knowledge-rich source network intrusion domain to facilitate more accurate intrusion detection for the data-scarce target IoT intrusion domain.
no code implementations • 23 May 2023 • Yuming Huang, Yi Gu, Chengzhong Xu, Hui Kong
Specifically, semantic segmentation is achieved by a new mask-range transformer network in a mask-classfication paradigm.
no code implementations • 25 Mar 2023 • Jiashu Wu, Yang Wang, Hao Dai, Chengzhong Xu, Kenneth B. Kent
The ABRSI achieves fine-grained intrusion knowledge transfer via adaptive bi-recommendation matching.
no code implementations • 24 Jan 2023 • Jiashu Wu, Hao Dai, Yang Wang, Kejiang Ye, Chengzhong Xu
In this paper, a Geometric Graph Alignment (GGA) approach is leveraged to mask the geometric heterogeneities between domains for better intrusion knowledge transfer.
no code implementations • 1 Jan 2023 • Xingwu Sun, Hongyin Tang, Chengzhong Xu
Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type.
no code implementations • 26 Dec 2022 • Kafeng Wang, Pengyang Wang, Chengzhong Xu
Specifically, we construct the AFE pipeline based on reinforcement learning setting, where each feature is assigned an agent to perform feature transformation \com{and} selection, and the evaluation score of the produced features in downstream tasks serve as the reward to update the policy.
no code implementations • 28 Oct 2022 • Jiashu Wu, Yang Wang, Binhui Xie, Shuang Li, Hao Dai, Kejiang Ye, Chengzhong Xu
The scenario semantic endows source NI and II domain with characteristics from each other to ease the knowledge transfer process via a confused domain discriminator and categorical distribution knowledge preservation.
no code implementations • 9 Aug 2022 • Jiashu Wu, Hao Dai, Yang Wang, Shigen Shen, Chengzhong Xu
With the fast growing quantity of data generated by smart devices and the exponential surge of processing demand in the Internet of Things (IoT) era, the resource-rich cloud centres have been utilised to tackle these challenges.
no code implementations • 24 Jun 2022 • Yi Gu, Yuming Huang, Chengzhong Xu, Hui Kong
To answer this question, we propose a unified mask-classification model, MaskRange, for the range-view based LiDAR semantic and panoptic segmentation.
1 code implementation • 3 Jun 2022 • Shuai Wang, Chengyang Li, Derrick Wing Kwan Ng, Yonina C. Eldar, H. Vincent Poor, Qi Hao, Chengzhong Xu
However, it is challenging to determine the network resources and road sensor placements for multi-stage training with multi-modal datasets in multi-variant scenarios.
no code implementations • 26 May 2022 • Xingjian Li, Pengkun Yang, Yangcheng Gu, Xueying Zhan, Tianyang Wang, Min Xu, Chengzhong Xu
We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients.
no code implementations • 12 Apr 2022 • Zhixing Hou, Yan Yan, Chengzhong Xu, Hui Kong
In the SRT, we extract the local feature for each point cell.
1 code implementation • 24 Mar 2022 • Qi Li, Weining Wang, Chengzhong Xu, Zhenan Sun
In addition, semantic information is introduced into the semantic-guided fusion module to control the swapped area and model the pose and expression more accurately.
no code implementations • ICCV 2023 • Andong Deng, Xingjian Li, Di Hu, Tianyang Wang, Haoyi Xiong, Chengzhong Xu
Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations.
no code implementations • 2 Mar 2022 • Yi Gu, Hongzhi Cheng, Kafeng Wang, Dejing Dou, Chengzhong Xu, Hui Kong
In this paper, we propose a learning-based moving-object tracking method utilizing our newly developed LiDAR sensor, Frequency Modulated Continuous Wave (FMCW) LiDAR.
1 code implementation • 9 Aug 2021 • Jiexia Ye, Juanjuan Zhao, Furong Zheng, Chengzhong Xu
Due to the delayed effect in latest complete OD flow collection, complex spatiotemporal correlations of OD flows in high dimension, it is more challengeable than other traffic prediction tasks of time series.
no code implementations • 20 Jul 2021 • Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Fan Liu, Xiaohui Peng, Tony Xiao Han, Chengzhong Xu
Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition.
no code implementations • 13 Jul 2021 • Zhenning Li, Chengzhong Xu, Guohui Zhang
Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy.
1 code implementation • 4 Jul 2021 • Jiexia Ye, Furong Zheng, Juanjuan Zhao, Kejiang Ye, Chengzhong Xu
Our main novelties are three aspects: (1) We enrich the spatiotemporal information of model inputs by fusing multi-view features (time, location and traffic states) (2) We build multiple kinds of spatial correlations based on both prior knowledge and data-driven knowledge to improve model performance especially in insufficient or noisy data cases.
1 code implementation • 24 Jun 2021 • Kahou Tam, Li Li, Bo Han, Chengzhong Xu, Huazhu Fu
Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy.
no code implementations • 24 Jun 2021 • Zhiheng Zhong, Minxian Xu, Maria Alejandra Rodriguez, Chengzhong Xu, Rajkumar Buyya
Containerization is a lightweight application virtualization technology, providing high environmental consistency, operating system distribution portability, and resource isolation.
1 code implementation • CVPR 2021 • Yuhao Zhu, Qi Li, Jian Wang, Chengzhong Xu, Zhenan Sun
Extensive experiments demonstrate the superiority of MegaFS and the first megapixel level face swapping database is released for research on DeepFake detection and face image editing in the public domain.
Ranked #8 on Face Swapping on FaceForensics++
no code implementations • 25 Mar 2021 • Xingjian Li, Haoyi Xiong, Chengzhong Xu, Dejing Dou
Performing mixup for transfer learning with pre-trained models however is not that simple, a high capacity pre-trained model with a large fully-connected (FC) layer could easily overfit to the target dataset even with samples-to-labels mixed up.
no code implementations • 5 Feb 2021 • Wenting Zou, Li Li, Zichen Xu, Chengzhong Xu
To address the conflict between learning SLO and energy efficiency, we propose DEAL, an energy efficient learning system that saves energy and preserves privacy with a decremental learning design.
1 code implementation • ICCV 2021 • Huajun Liu, Xiangyu Miao, Christoph Mertz, Chengzhong Xu, Hui Kong
The CrackFormer is composed of novel attention modules in a SegNet-like encoder-decoder architecture.
no code implementations • 16 Oct 2020 • Xingjian Li, Di Hu, Xuhong LI, Haoyi Xiong, Zhi Ye, Zhipeng Wang, Chengzhong Xu, Dejing Dou
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
no code implementations • 26 Apr 2020 • Xingjian Li, Haoyi Xiong, Haozhe An, Dejing Dou, Chengzhong Xu
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).