# One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment Source: [One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:11:37.721Z Authors: Qigong Sun, Xiufang Li, Yan Ren, Zhongjian Huang, Xu Liu, Licheng Jiao, Fang Liu Published: 2021-05-04T08:10:50.000Z ## Abstract As an effective technique to achieve the implementation of deep neural networks in edge devices, model quantization has been successfully applied in many practical applications. No matter the methods of quantization aware training (QAT) or post-training quantization (PTQ), they all depend on the target bit-widths. When the precision of quantization is adjusted, it is necessary to fine-tune the quantized model or minimize the quantization noise, which brings inconvenience in practical applications. In this work, we propose a method to train a model for all quantization that supports diverse bit-widths (e.g., form 8-bit to 1-bit) to satisfy the online quantization bit-width adjustment. It is hot-swappable that can provide specific quantization strategies for different candidates through multiscale quantization. We use wavelet decomposition and reconstruction to increase the diversity of weights, thus significantly improving the performance of each quantization candidate, especially at ultra-low bit-widths (e.g., 3-bit, 2-bit, and 1-bit). Experimental results on ImageNet and COCO show that our method can achieve accuracy comparable performance to dedicated models trained at the same precision. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()