Places: A 10 Million Image Database for Scene Recognition

• Main Authors: Zhou, Bolei (Author), Lapedriza Garcia, Agata (Author), Khosla, Aditya (Author), Oliva, Aude (Author), Torralba, Antonio (Author)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers, 2019-11-20T17:18:38Z.
• Subjects: Article
• Online Access: Get fulltext

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. Keywords: Scene classification; visual recognition; deep learning; deep feature; image dataset
National Science Foundation (U.S.) (Grant 1016862)
National Science Foundation (U.S.) (Grant 1524817)
United States. Assistant Secretary of Defense for Research and Engineering. Basic Research Office (United States. Office of Naval Research (Grant N00014-16-1-3116)