arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.14642cs.CV
收藏

SPIQ:无数据每通道静态输入Quantization

SPIQ: Data-Free Per-Channel Static Input Quantization

Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Datakalab(Datakalab公司);Valeo(法雷奥)

Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

摘要:

计算昂贵的神经网络在计算机视觉中无处不在,高效推理的解决方案在机器学习社区中引起了越来越多的关注。这种解决方案的示例包括量化,即将处理值(权重和输入)从浮点转换成整数,例如int 8或int 4。同时,隐私问题的兴起促使人们研究侵入性更小的加速方法,例如预训练模型权重和激活的无数据量化。先前的方法要么利用统计信息以静态方式推导激活的标量范围和缩放因子,要么动态地针对每个层的每个输入动态地调整该范围(也称为激活):后者通常在明显较慢的推断范围内更准确。在这项工作中,我们认为,静态输入量化可以达到动态方法的精度水平,通过每通道输入量化方案,允许一个更精细地保持跨通道动态。我们通过对多个计算机视觉问题(例如ImageNet分类,Pascal VOC目标检测以及CityScapes语义分割)的全面实证评估表明,所提出的方法(称为SPIQ)实现了与静态推理速度相媲美的动态方法的准确性,在每个基准上都显着优于最先进的量化方法。

英文摘要:

Computationally expensive neural networks are ubiquitous in computer vision and solutions for efficient inference have drawn a growing attention in the machine learning community. Examples of such solutions comprise quantization, i.e. converting the processing values (weights and inputs) from floating point into integers e.g. int8 or int4. Concurrently, the rise of privacy concerns motivated the study of less invasive acceleration methods, such as data-free quantization of pre-trained models weights and activations. Previous approaches either exploit statistical information to deduce scalar ranges and scaling factors for the activations in a static manner, or dynamically adapt this range on-the-fly for each input of each layers (also referred to as activations): the latter generally being more accurate at the expanse of significantly slower inference. In this work, we argue that static input quantization can reach the accuracy levels of dynamic methods by means of a per-channel input quantization scheme that allows one to more finely preserve cross-channel dynamics. We show through a thorough empirical evaluation on multiple computer vision problems (e.g. ImageNet classification, Pascal VOC object detection as well as CityScapes semantic segmentation) that the proposed method, dubbed SPIQ, achieves accuracies rivalling dynamic approaches with static-level inference speed, significantly outperforming state-of-the-art quantization methods on every benchmark.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑