Quantised neural networks (QNNs) shrink models and reduce inference energy through low-bit arithmetic, yet most still depend on a running statistics batch normalisation (BN) layer, preventing true integer-only deployment. Prior attempts remove BN by parameter folding or tailored initialisation; while helpful, they rarely recover BN's stability and accuracy and often impose bespoke constraints. We present a BN-free, fully integer QNN trained via a progressive, layer-wise distillation scheme that slots into existing low-bit pipelines. Starting from a pretrained BN-enabled teacher, we use layer-wise targets and progressive compensation to train a student that performs inference exclusively with integer arithmetic and contains no BN operations. On ImageNet with AlexNet, the BN-free model attains competitive Top-1 accuracy under aggressive quantisation. The procedure integrates directly with standard quantisation workflows, enabling end-to-end integer-only inference for resource-constrained settings such as edge and embedded devices.

翻译：量化神经网络通过低比特运算压缩模型并降低推理能耗，然而大多数仍依赖运行统计的批归一化层，阻碍了真正的纯整数部署。先前研究尝试通过参数折叠或定制初始化消除BN层；虽有一定效果，但很少能恢复BN的稳定性与精度，且常引入特殊约束。本文提出一种无BN的全整数量化神经网络，通过渐进式逐层蒸馏方案进行训练，可直接嵌入现有低比特流程。从预训练带BN的教师网络出发，我们采用逐层目标与渐进补偿机制训练学生网络，使其完全使用整数算术执行推理且不含BN操作。在ImageNet数据集上使用AlexNet架构，该无BN模型在激进量化条件下获得了具有竞争力的Top-1准确率。该方法可直接整合至标准量化流程，为边缘计算与嵌入式设备等资源受限场景实现端到端的纯整数推理。