Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs
School of Artificial Intelligence and Robotics, Quanzhou Institute of Industrial Design and Machine Intelligence Innovation, Hunan University(人工智能与机器人学院、泉州工业设计与智能机械创新研究院、湖南大学);College of Engineering and Design, Hunan Normal University(工程与设计学院、湖南师范大学);College of Intelligence Science and Technology, National University of Defense Technology(智能科学与技术学院、国防科技大学);School of Computing and Information Systems, The University of Melbourne(计算与信息学院、墨尔本大学)
Multi-Layer Perceptron (MLP) models are the foundation of contemporary point cloud processing. However, their complex network architectures obscure the source of their strength and limit the application of these models. In this article, we develop a two-stage abstraction and refinement (ABS-REF) view for modular feature extraction in point cloud processing. This view elucidates that whereas the early models focused on ABS stages, the more recent techniques devise sophisticated REF stages to attain performance advantages. Then, we propose a High-dimensional Positional Encoding (HPE) module to explicitly utilize intrinsic positional information, extending the ``positional encoding'' concept from Transformer literature. HPE can be readily deployed in MLP-based architectures and is compatible with transformer-based methods. Within our ABS-REF view, we rethink local aggregation in MLP-based methods and propose replacing time-consuming local MLP operations, which are used to capture local relationships among neighbors. Instead, we use non-local MLPs for efficient non-local information updates, combined with the proposed HPE for effective local information representation. We leverage our modules to develop HPENets, a suite of MLP networks that follow the ABS-REF paradigm, incorporating a scalable HPE-based REF stage. Extensive experiments on seven public datasets across four different tasks show that HPENets deliver a strong balance between efficiency and effectiveness. Notably, HPENet surpasses PointNeXt, a strong MLP-based counterpart, by 1.1% mAcc, 4.0% mIoU, 1.8% mIoU, and 0.2% Cls. mIoU, with only 50.0%, 21.5%, 23.1%, 44.4% of FLOPs on ScanObjectNN, S3DIS, ScanNet, and ShapeNetPart, respectively. Source code is available at https://github.com/zouyanmei/HPENet_v2.git.
Weierstrass Positional Encoding for Vision Transformers
School of Mathematics and Data Science, Jiangnan University(江南大学数学与数据科学学院);School of Artificial Intelligence and Computer Science, Jiangnan University(江南大学人工智能与计算机科学学院)
On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding
University of Hong Kong(香港大学);University of British Columbia(不列颠哥伦比亚大学);City University of Hong Kong(香港城市大学);Zhejiang University(浙江大学);Texas A&M University(德克萨斯农工大学)
Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
University of Science and Technology of China(中国科学技术大学);Institute of Microelectronics, Chinese Academy of Sciences(中国科学院微电子研究所);Singapore Management University(新加坡管理大学);University of Manchester(曼彻斯特大学)
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);University of California, Los Angeles(加州大学洛杉矶分校);The University of Queensland(昆士兰大学);Shanghai University of Finance and Economics(上海财经大学)
Anisotropic Fourier Features for Positional Encoding in Medical Imaging
Center of Digital Health, Berlin Institute of Health at Charité – Universitätsmedizin Berlin(柏林查理医院数字健康中心);Charité – Universitätsmedizin Berlin(柏林查理医院大学医学中心);Freie Universität Berlin(柏林自由大学);Humboldt-Universität zu Berlin(柏林洪堡大学)
ViTaPEs: Visuotactile Position Encodings for Cross-Modal Alignment in Multimodal Transformers
Chair of Cyber-Physical Systems(感知系统教授席位);Institute of Machine Learning and Neural Computation(机器学习与神经计算研究所);Technical University of Leoben(莱比锡技术大学);Graz University of Technology(格拉茨技术大学)