Object detectors emerge in Deep Scene CNNs
With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for cont...
| मुख्य लेखकों: | , , , , |
|---|---|
| अन्य लेखक: | |
| स्वरूप: | लेख |
| भाषा: | en_US |
| प्रकाशित: |
2015
|
| ऑनलाइन पहुंच: | http://hdl.handle.net/1721.1/96942 https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0002-3570-4396 https://orcid.org/0000-0003-4915-0256 |
| _version_ | 1826216890785071104 |
|---|---|
| author | Zhou, Bolei Khosla, Aditya Lapedriza Garcia, Agata 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 Khosla, Aditya Lapedriza Garcia, Agata Oliva, Aude Torralba, Antonio |
| author_sort | Zhou, Bolei |
| collection | MIT |
| description | With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects. |
| first_indexed | 2024-09-23T16:54:45Z |
| format | Article |
| id | mit-1721.1/96942 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:54:45Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | mit-1721.1/969422022-10-03T09:05:06Z Object detectors emerge in Deep Scene CNNs Zhou, Bolei Khosla, Aditya Lapedriza Garcia, Agata Oliva, Aude Torralba, Antonio Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Zhou, Bolei Khosla, Aditya Lapedriza Garcia, Agata Oliva, Aude Torralba, Antonio With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects. National Science Foundation (U.S.) (Grant 1016862) United States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933) Google (Firm) Xerox Corporation 2015-05-08T16:56:01Z 2015-05-08T16:56:01Z 2015-05 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/96942 Bolei, Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. "Object detectors emerge in Deep Scene CNNs." 2015 International Conference on Learning Representations, May 7-9, 2015. https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0002-3570-4396 https://orcid.org/0000-0003-4915-0256 en_US http://www.iclr.cc/doku.php?id=iclr2015:main#conference_schedule Proceedings of the 2015 International Conference on Learning Representations Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf arXiv |
| spellingShingle | Zhou, Bolei Khosla, Aditya Lapedriza Garcia, Agata Oliva, Aude Torralba, Antonio Object detectors emerge in Deep Scene CNNs |
| title | Object detectors emerge in Deep Scene CNNs |
| title_full | Object detectors emerge in Deep Scene CNNs |
| title_fullStr | Object detectors emerge in Deep Scene CNNs |
| title_full_unstemmed | Object detectors emerge in Deep Scene CNNs |
| title_short | Object detectors emerge in Deep Scene CNNs |
| title_sort | object detectors emerge in deep scene cnns |
| url | http://hdl.handle.net/1721.1/96942 https://orcid.org/0000-0002-0007-3352 https://orcid.org/0000-0002-3570-4396 https://orcid.org/0000-0003-4915-0256 |
| work_keys_str_mv | AT zhoubolei objectdetectorsemergeindeepscenecnns AT khoslaaditya objectdetectorsemergeindeepscenecnns AT lapedrizagarciaagata objectdetectorsemergeindeepscenecnns AT olivaaude objectdetectorsemergeindeepscenecnns AT torralbaantonio objectdetectorsemergeindeepscenecnns |