Learning Deep Features for Scene Recognition using Places Database

Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a context for object recognition. Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CNN...

Full description

Bibliographic Details
Main Authors: Zhou, Bolei, Lapedriza Garcia, Agata, Xiao, Jianxiong, Torralba, Antonio, Oliva, Aude
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:en_US
Published: Neural Information Processing Systems Foundation 2015
Online Access:http://hdl.handle.net/1721.1/96941
https://orcid.org/0000-0002-3570-4396
https://orcid.org/0000-0003-4915-0256
_version_ 1826209444549099520
author Zhou, Bolei
Lapedriza Garcia, Agata
Xiao, Jianxiong
Torralba, Antonio
Oliva, Aude
author2 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
author_facet Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Zhou, Bolei
Lapedriza Garcia, Agata
Xiao, Jianxiong
Torralba, Antonio
Oliva, Aude
author_sort Zhou, Bolei
collection MIT
description Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a context for object recognition. Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CNNs) for learning high-level features, performance at scene recognition has not attained the same level of success. This may be because current deep features trained from ImageNet are not competitive enough for such tasks. Here, we introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes. We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity. Using CNN, we learn deep features for scene recognition tasks, and establish new state-of-the-art results on several scene-centric datasets. A visualization of the CNN layers' responses allows us to show differences in the internal representations of object-centric and scene-centric networks.
first_indexed 2024-09-23T14:22:36Z
format Article
id mit-1721.1/96941
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T14:22:36Z
publishDate 2015
publisher Neural Information Processing Systems Foundation
record_format dspace
spelling mit-1721.1/969412022-10-01T20:54:16Z Learning Deep Features for Scene Recognition using Places Database Zhou, Bolei Lapedriza Garcia, Agata Xiao, Jianxiong Torralba, Antonio Oliva, Aude Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Zhou, Bolei Lapedriza Garcia, Agata Torralba, Antonio Oliva, Aude Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a context for object recognition. Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CNNs) for learning high-level features, performance at scene recognition has not attained the same level of success. This may be because current deep features trained from ImageNet are not competitive enough for such tasks. Here, we introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes. We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity. Using CNN, we learn deep features for scene recognition tasks, and establish new state-of-the-art results on several scene-centric datasets. A visualization of the CNN layers' responses allows us to show differences in the internal representations of object-centric and scene-centric networks. National Science Foundation (U.S.) (Grant 1016862) United States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933) Google (Firm) Xerox Corporation Grant TIN2012-38187-C03-02 United States. Intelligence Advanced Research Projects Activity (United States. Air Force Research Laboratory Contract FA8650-12-C-7211) 2015-05-08T16:44:39Z 2015-05-08T16:44:39Z 2014 Article http://purl.org/eprint/type/ConferencePaper 1049-5258 http://hdl.handle.net/1721.1/96941 Zhou, Bolei, Agata Lapedriza, Jianxiong Xiao, Antonio Torralba, and Aude Oliva. "Learning Deep Features for Scene Recognition using Places Database." Advances in Neural Information Processing Systems (NIPS) 27, 2014. https://orcid.org/0000-0002-3570-4396 https://orcid.org/0000-0003-4915-0256 en_US http://papers.nips.cc/paper/5349-learning-deep-features-for-scene-recognition-using-places-database Advances in Neural Information Processing Systems (NIPS) 27 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Neural Information Processing Systems Foundation MIT web domain
spellingShingle Zhou, Bolei
Lapedriza Garcia, Agata
Xiao, Jianxiong
Torralba, Antonio
Oliva, Aude
Learning Deep Features for Scene Recognition using Places Database
title Learning Deep Features for Scene Recognition using Places Database
title_full Learning Deep Features for Scene Recognition using Places Database
title_fullStr Learning Deep Features for Scene Recognition using Places Database
title_full_unstemmed Learning Deep Features for Scene Recognition using Places Database
title_short Learning Deep Features for Scene Recognition using Places Database
title_sort learning deep features for scene recognition using places database
url http://hdl.handle.net/1721.1/96941
https://orcid.org/0000-0002-3570-4396
https://orcid.org/0000-0003-4915-0256
work_keys_str_mv AT zhoubolei learningdeepfeaturesforscenerecognitionusingplacesdatabase
AT lapedrizagarciaagata learningdeepfeaturesforscenerecognitionusingplacesdatabase
AT xiaojianxiong learningdeepfeaturesforscenerecognitionusingplacesdatabase
AT torralbaantonio learningdeepfeaturesforscenerecognitionusingplacesdatabase
AT olivaaude learningdeepfeaturesforscenerecognitionusingplacesdatabase