用可学习分段线性函数建模神经元膜电位，提升事件相机视觉性能
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
- 用可学习参数的分段线性函数模拟神经元膜电位
- 在事件相机任务中达到当前最优表现，涵盖轨迹预测等
- 适合做事件相机视觉、类脑计算的研究者参考
我们提出用于时序视觉推理的参数化分段线性网络（PPLNs）。受类脑神经行为原理启发，PPLNs 适用于事件相机采集的数据，这类相机旨在模拟人类视网膜的神经活动。本文探讨如何用带可学习系数的参数化分段线性函数表示人工神经元的膜电位，这一设计呼应了近期由柯尔莫哥洛夫-阿诺德网络（KANs）推动的以可学习参数函数构建深度模型的思想。实验表明，PPLNs 在事件相机和图像基础视觉任务中均表现卓越，包括转向预测、人体姿态估计和运动去模糊。代码已开源：https://github.com/chensong1995/PPLN。
原文摘要 · Abstract (English)
We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are ideal for processing data captured by event cameras, which are built to simulate neural activities in the human retina. We discuss how to represent the membrane potential of an artificial neuron by a parametric piecewise linear function with learnable coefficients. This design echoes the idea of building deep models from learnable parametric functions recently popularized by Kolmogorov-Arnold Networks (KANs). Experiments demonstrate the state-of-the-art performance of PPLNs in event-based and image-based vision applications, including steering prediction, human pose estimation, and motion deblurring. The source code of our implementation is available at https://github.com/chensong1995/PPLN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。