We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model, informed by work on neural scaling laws, and infer a decomposition of progress into the scaling of compute, data, and algorithms. Using Shapley values to attribute performance improvements, we find that algorithmic improvements have been roughly as important as the scaling of compute for progress computer vision. Our estimates indicate that algorithmic innovations mostly take the form of compute-augmenting algorithmic advances (which enable researchers to get better performance from less compute), not data-augmenting algorithmic advances. We find that compute-augmenting algorithmic advances are made at a pace more than twice as fast as the rate usually associated with Moore's law. In particular, we estimate that compute-augmenting innovations halve compute requirements every nine months (95\% confidence interval: 4 to 25 months).

翻译：我们研究了ImageNet（或许是最著名的计算机视觉测试平台）上图像分类的算法进展。基于神经缩放定律的研究，我们构建了一个模型，并将进展分解为计算、数据和算法的缩放效应。使用夏普利值来归因性能提升，我们发现算法改进与计算规模的扩展对计算机视觉进步的贡献大致相当。我们的估计表明，算法创新主要体现为增强计算的算法进步（使研究人员能够用更少的计算获得更好的性能），而非增强数据的算法进步。我们发现，增强计算的算法进步速度是通常与摩尔定律相关速度的两倍以上。具体而言，我们估计增强计算的创新每九个月使计算需求减半（95%置信区间：4至25个月）。