论文标题
evopose2d：使用加速神经进化以重量转移来推动2D人姿势估计的边界
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
论文作者
论文摘要
事实证明，神经架构搜索在设计高效卷积神经网络方面非常有效，这些卷积神经网络比手工设计的网络更适合移动部署。假设神经结构搜索具有人为估计的巨大潜力，我们探索了神经进化的应用，神经进化是受生物进化启发的神经架构搜索形式，它首次设计了2D人类姿势网络。此外，我们提出了一种新的体重转移方案，使我们能够以灵活的方式加速神经进化。我们的方法生成的网络设计比最先进的手工设计的网络更有效，更准确。实际上，生成的网络在更高的分辨率上使用比以前的手工设计的网络更少的计算处理图像，从而使我们能够突破2D人类姿势估计的边界。我们通过NeuroCopose的基本网络（我们称为evopose2d-s）实现了与简单的基础相当的精度，而在文件大小方面的速度更快为50％，小于12.7倍。我们最大的网络Evopose2D-L在Microsoft Coco Keypoints基准测试上实现了新的最先进的准确性，比其最近的竞争对手小4.3倍，并且具有相似的推理速度。该代码可在https://github.com/wmcnally/evopose2d上公开获取。
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.
