{"ID":2827540,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16476","arxiv_id":"2512.16476","title":"Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning","abstract":"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.","short_abstract":"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 rare...","url_abs":"https://arxiv.org/abs/2512.16476","url_pdf":"https://arxiv.org/pdf/2512.16476v1","authors":"[\"Pengfei Sun\",\"Wenyu Jiang\",\"Piew Yoong Chee\",\"Paul Devos\",\"Dick Botteldooren\"]","published":"2025-12-18T12:47:18Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"eess.SP\"]","methods":"[]","has_code":false}