Places: A 10 Million Image Database for Scene Recognition
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, lab...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers
2019
|
| Online Access: | https://hdl.handle.net/1721.1/122983 |
| _version_ | 1811097673430728704 |
|---|---|
| author | Zhou, Bolei Lapedriza Garcia, Agata Khosla, Aditya Oliva, Aude Torralba, Antonio |
| 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 Khosla, Aditya Oliva, Aude Torralba, Antonio |
| author_sort | Zhou, Bolei |
| collection | MIT |
| description | 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 |
| first_indexed | 2024-09-23T17:03:05Z |
| format | Article |
| id | mit-1721.1/122983 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T17:03:05Z |
| publishDate | 2019 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/1229832022-09-29T23:19:32Z Places: A 10 Million Image Database for Scene Recognition Zhou, Bolei Lapedriza Garcia, Agata Khosla, Aditya Oliva, Aude Torralba, Antonio Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory 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) 2019-11-20T17:18:38Z 2019-11-20T17:18:38Z 2017-07-04 2019-07-11T17:20:57Z Article http://purl.org/eprint/type/JournalArticle 0162-8828 2160-9292 1939-3539 https://hdl.handle.net/1721.1/122983 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 en https://doi.org/10.1109/tpami.2017.2723009 IEEE Transactions on Pattern Analysis and Machine Intelligence Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers arXiv |
| spellingShingle | Zhou, Bolei Lapedriza Garcia, Agata Khosla, Aditya Oliva, Aude Torralba, Antonio Places: A 10 Million Image Database for Scene Recognition |
| title | Places: A 10 Million Image Database for Scene Recognition |
| title_full | Places: A 10 Million Image Database for Scene Recognition |
| title_fullStr | Places: A 10 Million Image Database for Scene Recognition |
| title_full_unstemmed | Places: A 10 Million Image Database for Scene Recognition |
| title_short | Places: A 10 Million Image Database for Scene Recognition |
| title_sort | places a 10 million image database for scene recognition |
| url | https://hdl.handle.net/1721.1/122983 |
| work_keys_str_mv | AT zhoubolei placesa10millionimagedatabaseforscenerecognition AT lapedrizagarciaagata placesa10millionimagedatabaseforscenerecognition AT khoslaaditya placesa10millionimagedatabaseforscenerecognition AT olivaaude placesa10millionimagedatabaseforscenerecognition AT torralbaantonio placesa10millionimagedatabaseforscenerecognition |