Places: A 10 Million Image Database for Scene Recognition
Name
PAMI_places.pdf
Description
Accepted version
Size
10.34 MB
Format
Adobe PDF
Checksum (MD5)
1f7e5d257ff7ff6b2976ddc0888127f2
Author(s)
Zhou, Bolei
Lapedriza Garcia, Agata
Khosla, Aditya
Oliva, Aude
Torralba, Antonio
Date Issued
July 4, 2017
Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers
Citation
Zhou, Bolei et al. "Places: A 10 Million Image Database for Scene Recognition." IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 6 (June 2018): 1452-1464 © 2017 Institute of Electrical and Electronics Engineers
Version
Author's final manuscript
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. Keywords: Scene classification; visual recognition; deep learning; deep feature; image dataset
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/tpami.2017.2723009
