为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自香港中文大学(深圳)的点云形状分析方面的工作。该工作由李镇助理教授指导、论文共同第一作者占贺深博士生录制。 论文题目:Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis 作者列表:颜旭 (香港中文大学 (深圳)),占贺深 (香港中文大学 (深圳)),郑超达 (香港中文大学 (深圳)),高建焘 (上海大学),张瑞茂 (香港中文大学 (深圳)),崔曙光 (香港中文大学 (深圳)),李镇 (香港中文大学 (深圳)) B站观看网址: 论文摘要: Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud representation by fully taking advantages of images which inherently contain richer appearance information, e.g., texture, color, and shade. Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis. In practice, to effectively acquire auxiliary knowledge from view images, we develop a teacher-student framework and formulate the crossmodal learning as a knowledge distillation problem. PointCMT eliminates the distribution discrepancy between different modalities through novel feature and classifier enhancement criteria and avoids potential negative transfer effectively. Note that PointCMT effectively improves the point-only representation without architecture modification. Sufficient experiments verify significant gains on various datasets using appealing backbones, i.e., equipped with PointCMT, PointNet++ and PointMLP achieve state-of-the-art performance on two benchmarks, i.e., 94.4% and 86.7% accuracy on ModelNet40 and ScanObjectNN, respectively. 论文信息: [1] Xu Yan*, Heshen Zhan*, Chaoda Zheng, Jiantao Gao, Ruimao Zhang,Shuguang Cui, Zhen Li, Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis In NeurIPS, 2022. 论文链接: [https://arxiv.org/abs/2203.01730] 代码链接: [https://github.com/ZhanHeshen/PointCMT] 视频讲者简介: 占贺深,香港中文大学 (深圳)理工学院博士生。主要研究方向为非欧数据的表征学习与分析。 特别鸣谢本次论文速览主要组织者: 月度轮值AC:林迪 (天津大学)、胡鹏 (四川大学) 活动参与方式 1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们! 直播地址: https://live.bilibili.com/22300737; 历史视频观看地址: https://space.bilibili.com/562085182/ 2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ S群,群号:317920537); *注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。 3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。 4、您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。 |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-10-31 14:19 , Processed in 0.014510 second(s), 14 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.