论文标题
神经架构搜索是否需要标签？
Are Labels Necessary for Neural Architecture Search?
论文作者
论文摘要
通常使用图像及其相关标签发现计算机视觉中现有的神经网络体系结构（无论是由人类设计的）。在本文中，我们提出了一个问题：我们能否仅使用图像找到高质量的神经体系结构，但没有人类通知的标签？为了回答这个问题，我们首先定义了一种名为无监督的神经体系结构搜索（UNNA）的新设置。然后，我们进行了两组实验。在基于样本的实验中，我们使用有监督或无监督的目标培训大量（500）不同的体系结构，并发现具有和没有标签的带有和没有标签的体系结构排名高度相关。在基于搜索的实验中，我们使用各种无监督的目标运行建立了良好的NAS算法（DARTS），并报告未经标签搜索的体系结构与使用标签搜索的对应物具有竞争力。总之，这些结果表明了标签不是必需的可能令人惊讶的发现，仅图像统计数据就足以识别良好的神经体系结构。
Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels. In this paper, we ask the question: can we find high-quality neural architectures using only images, but no human-annotated labels? To answer this question, we first define a new setup called Unsupervised Neural Architecture Search (UnNAS). We then conduct two sets of experiments. In sample-based experiments, we train a large number (500) of diverse architectures with either supervised or unsupervised objectives, and find that the architecture rankings produced with and without labels are highly correlated. In search-based experiments, we run a well-established NAS algorithm (DARTS) using various unsupervised objectives, and report that the architectures searched without labels can be competitive to their counterparts searched with labels. Together, these results reveal the potentially surprising finding that labels are not necessary, and the image statistics alone may be sufficient to identify good neural architectures.
