科研之友
微信
新浪微博
Facebook
分享链接
摘要
It is a fundamental and vital task to enhance the perception capability of the point cloud learning net-work in 3D machine vision applications. Most existing methods utilize feature fusion and geometric transformation to improve point cloud learning without paying enough attention to mining further in-trinsic information across multiple network layers. Motivated to improve consistency between hierarchi-cal features and strengthen the perception capability of the point cloud network, we propose exploring whether maximizing the mutual information (MI) across shallow and deep layers is beneficial to improve representation learning on point clouds. A novel design of Maximizing Mutual Information (MMI) Mod-ule is proposed, which assists the training process of the main network to capture discriminative features of the input point clouds. Specifically, the MMI-based loss function is employed to constrain the differ-ences of semantic information in two hierarchical features extracted from the shallow and deep layers of the network. Extensive experiments show that our method is generally applicable to point cloud tasks, including classification, shape retrieval, indoor scene segmentation, 3D object detection, and completion, and illustrate the efficacy of our proposed method and its advantages over existing ones. Our source code is available at https://github.com/wendydidi/MMI.git.
