{"ID":2850628,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21403","arxiv_id":"2510.21403","title":"Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks","abstract":"Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve competitive performance in visual long-sequence modeling tasks. In artificial neural networks, the effective receptive field (ERF) serves as a valuable tool for analyzing feature extraction capabilities in visual long-sequence modeling. Inspired by this, we introduce the Spatio-Temporal Effective Receptive Field (ST-ERF) to analyze the ERF distributions across various Transformer-based SNNs. Based on the proposed ST-ERF, we reveal that these models suffer from establishing a robust global ST-ERF, thereby limiting their visual feature modeling capabilities. To overcome this issue, we propose two novel channel-mixer architectures: \\underline{m}ulti-\\underline{l}ayer-\\underline{p}erceptron-based m\\underline{ixer} (MLPixer) and \\underline{s}plash-and-\\underline{r}econstruct \\underline{b}lock (SRB). These architectures enhance global spatial ERF through all timesteps in early network stages of Transformer-based SNNs, improving performance on challenging visual long-sequence modeling tasks. Extensive experiments conducted on the Meta-SDT variants and across object detection and semantic segmentation tasks further validate the effectiveness of our proposed method. Beyond these specific applications, we believe the proposed ST-ERF framework can provide valuable insights for designing and optimizing SNN architectures across a broader range of tasks. The code is available at \\href{https://github.com/EricZhang1412/Spatial-temporal-ERF}{\\faGithub~EricZhang1412/Spatial-temporal-ERF}.","short_abstract":"Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve competitive performance in visual long-sequence modeling tasks. In artificial neu...","url_abs":"https://arxiv.org/abs/2510.21403","url_pdf":"https://arxiv.org/pdf/2510.21403v1","authors":"[\"Jieyuan Zhang\",\"Xiaolong Zhou\",\"Shuai Wang\",\"Wenjie Wei\",\"Hanwen Liu\",\"Qian Sun\",\"Malu Zhang\",\"Yang Yang\",\"Haizhou Li\"]","published":"2025-10-24T12:46:58Z","proceeding":"cs.NE","tasks":"[\"cs.NE\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":607824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850628,"paper_url":"https://arxiv.org/abs/2510.21403","paper_title":"Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks","repo_url":"https://github.com/EricZhang1412/Spatial-temporal-ERF","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}