We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings. End-to-end optimization of positional embedding parameters along with network weights leads to poor generalization performance. Instead, we develop a generic framework to learn the positional embedding based on the classic graph-Laplacian regularization, which can implicitly balance the trade-off between memorization and generalization. This framework is then used to propose a novel positional embedding scheme, where the hyperparameters are learned per coordinate (i.e, instance) to deliver optimal performance. We show that the proposed embedding achieves better performance with higher stability compared to the well-established random Fourier features (RFF). Further, we demonstrate that the proposed embedding scheme yields stable gradients, enabling seamless integration into deep architectures as intermediate layers.
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)
Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
African Institute for Mathematical Sciences (AIMS), Research and Innovation Centre, Rwanda(非洲数学科学研究所(AIMS),研究与创新中心,卢旺达);Graduate School of Engineering, The University of Tokyo, Japan(东京大学工学研究科,日本);Axiom Research Group Department of Applied Mathematics and Computational Science, NM-AIST, Tanzania(Axiom研究组应用数学与计算科学系,NM-AIST,坦桑尼亚)
MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy
Swiss Federal Institute of Technology Lausanne(瑞士联邦理工学院洛桑分校);Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)(可扩展数据与人工智能中心(ScaDS.AI));Technische Universität Dresden(德累斯顿技术大学)