Výsledky vyhledávání - "Huang, Shikun"

Report

FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving

Autor: Ye, Tengju, Jing, Wei, Hu, Chunyong, Huang, Shikun, Gao, Lingping, Li, Fangzhen, Wang, Jingke, Guo, Ke, Xiao, Wencong, Mao, Weibo, Zheng, Hang, Li, Kun, Chen, Junbo, Yu, Kaicheng

Building a multi-modality multi-task neural network toward accurate and robust performance is a de-facto standard in perception task of autonomous driving. However, leveraging such data from multiple sensors to jointly optimize the prediction and pla

Externí odkaz: http://arxiv.org/abs/2308.01006

Zobrazit plný text záznamu

Report

A Deep Learning Technique using a Sequence of Follow Up X-Rays for Disease classification

Autor: Vijayaraghavan, Sairamvinay, Haddad, David, Huang, Shikun, Choi, Seongwoo

The ability to predict lung and heart based diseases using deep learning techniques is central to many researchers, particularly in the medical field around the world. In this paper, we present a unique outlook of a very familiar problem of disease c

Externí odkaz: http://arxiv.org/abs/2203.15060

Zobrazit plný text záznamu

Report

Interpretable Compositional Convolutional Neural Networks

Autor: Shen, Wen, Wei, Zhihua, Huang, Shikun, Zhang, Binbin, Fan, Jiaqi, Zhao, Ping, Zhang, Quanshi

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order to learn f

Externí odkaz: http://arxiv.org/abs/2107.04474

Zobrazit plný text záznamu

Report

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing

Autor: Shen, Wen, Wei, Zhihua, Huang, Shikun, Zhang, Binbin, Chen, Panyue, Zhao, Ping, Zhang, Quanshi

In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer network architec

Externí odkaz: http://arxiv.org/abs/1911.09053

Zobrazit plný text záznamu

Report

3D-Rotation-Equivariant Quaternion Neural Networks

Autor: Shen, Wen, Zhang, Binbin, Huang, Shikun, Wei, Zhihua, Zhang, Quanshi

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain conditions, the

Externí odkaz: http://arxiv.org/abs/1911.09040

Zobrazit plný text záznamu