Data-free quantization is a task that compresses the neural network to low bit-width without access to original training data. Most existing data-free quantization methods cause severe performance degradation due to inaccurate activation clipping range and quantization error, especially for low bit-width. In this paper, we present a simple yet effective data-free quantization method with accurate activation clipping and adaptive batch normalization. Accurate activation clipping (AAC) improves the model accuracy by exploiting accurate activation information from the full-precision model. Adaptive batch normalization firstly proposes to address the quantization error from distribution changes by updating the batch normalization layer adaptively. Extensive experiments demonstrate that the proposed data-free quantization method can yield surprisingly performance, achieving 64.33% top-1 accuracy of ResNet18 on ImageNet dataset, with 3.7% absolute improvement outperforming the existing state-of-the-art methods.
翻译:无数据量化是一项任务,它将神经网络压缩到低位宽,而没有原始培训数据。大多数现有的无数据量化方法由于不准确的激活剪切范围以及特别是低位宽的定量误差而导致性能严重退化。在本文中,我们提出了一个简单而有效的无数据量化方法,精确的激活剪辑和适应性批量正常化。精确的激活剪辑(AAC)通过利用完全精准模型的准确激活信息来改进模型的准确性能。适应性批次标准化首先提议通过适应性地更新批次正常化层来解决分配变化造成的量化错误。广泛的实验表明,拟议的无数据量化方法可以产生令人惊讶的性能,在图像网络数据集上达到ResNet18最高至1的64.33%的精度,3.7%的绝对改进超过了现有的最先进的方法。