VALSE 论文速览 第106期：点云形状分析的跨模态训练策略

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：

https://www.bilibili.com/video/BV15M4y1r7qb/

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)