Places: A 10 Million Image Database for Scene Recognition
Top Cited Papers
Open Access
- 4 July 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 40 (6), 1452-1464
- https://doi.org/10.1109/tpami.2017.2723009
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
Funding Information
- US National Science Foundation (1016862 to A.O., 1524817 to A.T.)
- Basic Research Office of the Assistant Secretary of Defense for Research and Engineering
- Office of Naval Research (N00014-16-1-3116 to A.O.)
- MIT Big Data Initiative at CSAIL
- Toyota Research Institute / MIT CSAIL Joint Research Center, Google, Xerox and Amazon Awards
- NVIDIA Corporation
- Facebook Fellowship
This publication has 30 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Watson: Beyond Jeopardy!Artificial Intelligence, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categoriesComputer Vision and Image Understanding, 2007
- Deep BlueArtificial Intelligence, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- WordNetCommunications of the ACM, 1995
- Pictures and names: Making the connectionCognitive Psychology, 1984
- Measurement of DiversityNature, 1949