The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification performance at tasks such as visual object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories, comprising a large and diverse list of the types of environments encountered in the world. Using the state-of-the-art Convolutional Neural Networks (CNNs), we provide scene classification CNNs (Places-CNNs) as baselines, that significantly outperform the previous approaches. Visualization of the CNNs trained on Places shows that object detectors emerge as an intermediate representation of scene classification. With its high-coverage and high-diversity of exemplars, the Places Database along with the Places-CNNs offer a novel resource to guide future progress on scene recognition problems.

中文翻译：

---

地点：用于场景识别的千万张图像数据库


数百万项数据集计划的兴起使得需要大量数据的机器学习算法能够在视觉对象和场景识别等任务中达到接近人类的语义分类性能。在这里，我们描述地点数据库，这是一个包含 1000 万张场景照片的存储库，标有场景语义类别，包含世界上遇到的环境类型的大量且多样化的列表。使用最先进的卷积神经网络 (CNN)，我们提供场景分类 CNN (Places-CNN) 作为基线，其性能显着优于以前的方法。在 Places 上训练的 CNN 的可视化表明，对象检测器作为场景分类的中间表示出现。凭借其高覆盖率和高多样性的范例，Places 数据库以及 Places-CNN 提供了一种新颖的资源来指导场景识别问题的未来进展。