{"ID":5443761,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T13:50:35.156039308Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31695","arxiv_id":"2606.31695","title":"Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization","abstract":"The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state-of-the-art models introduce runtime multiplications, which weaken the hardware-efficiency motivation of SNNs. To address this tension, we identify catastrophic firing-rate decay as a primary cause of severe performance degradation in normalization-free SNNs. Guided by this insight, this work proposes the Intrinsically Stable SNN (IS-SNN) architecture, which removes activation-normalization layers by enforcing signal homeostasis through topology-aware weight standardization and modified residual connections. By folding the standardization operations into static weights offline, IS-SNN removes the runtime statistics tracking and multiplications introduced by activation normalization, restoring an accumulation-oriented inference datapath. Comprehensive experiments show that IS-SNN achieves performance competitive with or superior to computationally expensive dynamic BN techniques across VGG, ResNet, and Transformer-based models. Notably, it achieves a competitive accuracy of 68.05\\% on ImageNet and overcomes the severe depth limitations of prior BN-free attempts. Together with a 96.4\\% reduction in FPGA lookup table resource consumption for neuron implementations, these results support IS-SNN as a practical framework for building accurate and hardware-friendly deep neuromorphic systems.","short_abstract":"The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state-of-the-art models introduce runtime multiplications, which weaken the hardware-efficiency motivation of SNNs. To address this tension, we identify catastrophic firing-...","url_abs":"https://arxiv.org/abs/2606.31695","url_pdf":"https://arxiv.org/pdf/2606.31695v1","authors":"[\"Ruichen Ma\",\"Xiaoyang Zhang\",\"Jian Bai\",\"Guanchao Qiao\",\"Liwei Meng\",\"Ning Ning\",\"Yang Liu\",\"Shaogang Hu\"]","published":"2026-06-30T14:07:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}