Object detectors emerge in Deep Scene CNNs

• Main Authors: Zhou, Bolei (Contributor), Khosla, Aditya (Contributor), Lapedriza Garcia, Agata (Contributor), Oliva, Aude (Contributor), Torralba, Antonio (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: 2015-05-08T16:56:01Z.
• Subjects: Article
• Online Access: Get fulltext

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