Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks. Hypothesizing that neural architecture search holds great potential for human pose estimation, we explore the application of neuroevolution, a form of neural architecture search inspired by biological evolution, in the design of 2D human pose networks for the first time. Additionally, we propose a new weight transfer scheme that enables us to accelerate neuroevolution in a flexible manner. Our method produces network designs that are more efficient and more accurate than state-of-the-art hand-designed networks. In fact, the generated networks process images at higher resolutions using less computation than previous hand-designed networks at lower resolutions, allowing us to push the boundaries of 2D human pose estimation. Our base network designed via neuroevolution, which we refer to as EvoPose2D-S, achieves comparable accuracy to SimpleBaseline while being 50% faster and 12.7x smaller in terms of file size. Our largest network, EvoPose2D-L, achieves new state-of-the-art accuracy on the Microsoft COCO Keypoints benchmark, is 4.3x smaller than its nearest competitor, and has similar inference speed. The code is publicly available at https://github.com/wmcnally/evopose2d.
翻译:事实证明,神经结构的搜索在设计高效的进化神经网络方面非常有效,这些网络比手工设计的网络更适合移动部署。假设神经结构的搜索具有巨大的人造估计潜力,我们探索应用神经神经进化(一种由生物进化启发的神经结构搜索形式),这是首次在设计2D人造网络时由生物进化所启发的神经进化。此外,我们提出一个新的重量转换计划,使我们能够以灵活的方式加速神经进化。我们的方法产生的网络设计比手动设计最先进的网络更有效和更准确。事实上,生成的网络图像使用比以前手动设计的低分辨率网络较少的计算处理更高分辨率,使我们能够推动2D人造估计的界限。我们通过神经进化设计的基础网络,我们称之为EvoPose2D-S, 实现与简单Baseline相似的精确度,同时速度更快,12.7x文件大小。我们最大的网络,EvoPose2D-L, 实现了新的州/州级的图像处理过程,比以前在较低的分辨率/州/州级标准中,在微软CO/州/州基点上有类似的最新精确度。