STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Zeqi, Zhu, Zizheng, Yu, Yingchao, Huang, Yanchen, Lv, Changze, Tang, Junfeng, Yu, Zhaofei, Jin, Yaochu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915436593938432
author Zheng, Zeqi
Zhu, Zizheng
Yu, Yingchao
Huang, Yanchen
Lv, Changze
Tang, Junfeng
Yu, Zhaofei
Jin, Yaochu
author_facet Zheng, Zeqi
Zhu, Zizheng
Yu, Yingchao
Huang, Yanchen
Lv, Changze
Tang, Junfeng
Yu, Zhaofei
Jin, Yaochu
contents Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \mbox{Artificial} Neural Networks (ANNs) due to the binary nature of spike trains. Recent efforts have introduced deep-level feedback loops to transmit high-level semantic information to narrow this gap. However, these designs often span \mbox{multiple} deep layers, resulting in costly feature transformations, higher parameter overhead, increased energy consumption, and longer inference latency. To address this issue, we propose Shallow-level Temporal Feedback (STF), a lightweight plug-and-play module for the encoding layer, which consists of Temporal-Spatial Position Embedding (TSPE) and Temporal Feedback (TF). Extensive experiments show that STF consistently improves performance across various Transformer-based SNN backbones on static datasets, including CIFAR-10, CIFAR-100, and ImageNet-1K, under different spike timestep settings. Further analysis reveals that STF enhances the diversity of spike patterns, which is key to performance gain. Moreover, evaluations on adversarial robustness and temporal sensitivity confirm that STF outperforms direct coding and its variants, highlighting its potential as a new spike encoding scheme for static scenarios. Our code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00387
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers
Zheng, Zeqi
Zhu, Zizheng
Yu, Yingchao
Huang, Yanchen
Lv, Changze
Tang, Junfeng
Yu, Zhaofei
Jin, Yaochu
Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \mbox{Artificial} Neural Networks (ANNs) due to the binary nature of spike trains. Recent efforts have introduced deep-level feedback loops to transmit high-level semantic information to narrow this gap. However, these designs often span \mbox{multiple} deep layers, resulting in costly feature transformations, higher parameter overhead, increased energy consumption, and longer inference latency. To address this issue, we propose Shallow-level Temporal Feedback (STF), a lightweight plug-and-play module for the encoding layer, which consists of Temporal-Spatial Position Embedding (TSPE) and Temporal Feedback (TF). Extensive experiments show that STF consistently improves performance across various Transformer-based SNN backbones on static datasets, including CIFAR-10, CIFAR-100, and ImageNet-1K, under different spike timestep settings. Further analysis reveals that STF enhances the diversity of spike patterns, which is key to performance gain. Moreover, evaluations on adversarial robustness and temporal sensitivity confirm that STF outperforms direct coding and its variants, highlighting its potential as a new spike encoding scheme for static scenarios. Our code will be released upon acceptance.
title STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers
topic Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.00387