Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: He, Huaxu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914176130088960
author He, Huaxu
author_facet He, Huaxu
contents Handling static images that lack inherent temporal dynamics remains a fundamental challenge for spiking neural networks (SNNs). In directly trained SNNs, static inputs are typically repeated across time steps, causing the temporal dimension to collapse into a rate like representation and preventing meaningful temporal modeling. This work revisits the reported performance gap between direct and rate based encodings and shows that it primarily stems from convolutional learnability and surrogate gradient formulations rather than the encoding schemes themselves. To illustrate this mechanism level clarification, we introduce a minimal learnable temporal encoding that adds adaptive phase shifts to induce meaningful temporal variation from static inputs.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks
He, Huaxu
Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Handling static images that lack inherent temporal dynamics remains a fundamental challenge for spiking neural networks (SNNs). In directly trained SNNs, static inputs are typically repeated across time steps, causing the temporal dimension to collapse into a rate like representation and preventing meaningful temporal modeling. This work revisits the reported performance gap between direct and rate based encodings and shows that it primarily stems from convolutional learnability and surrogate gradient formulations rather than the encoding schemes themselves. To illustrate this mechanism level clarification, we introduce a minimal learnable temporal encoding that adds adaptive phase shifts to induce meaningful temporal variation from static inputs.
title Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks
topic Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.01687