“Places: A 10 Million Image Database for Scene Recognition” (2017), by Bolei Zhou et al. Computer Science research paper. Original abstract below, unchanged. No free PDF was found.

Places: A 10 Million Image Database for Scene Recognition

Bolei Zhou, Àgata Lapedriza, Aditya Khosla et al. · July 4, 2017 · Computer Science

Abstract

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.

Source page DOI: 10.1109/tpami.2017.2723009