Learning Deep Features for Discriminative Localization
Name
Torralba_Learn deep.pdf
Size
2.43 MB
Format
Adobe PDF
Checksum (MD5)
e3d14a37a26a282fdfe2c331e7ee0fdd
Author(s)
Zhou, Bolei
Khosla, Aditya
Lapedriza Garcia, Agata
Oliva, Aude
Torralba, Antonio
Date Issued
December 2016
Journal
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Zhou, Bolei, et al. "Learning Deep Features for Discriminative Localization." 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June, 2016, Las Vegas, NV, IEEE, 2016, pp. 2921–29.
Version
Original manuscript
Abstract
In this work, we revisit the global average pooling layer proposed in, and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on imagelevel labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that exposes the implicit attention of CNNs on an image. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014 without training on any bounding box annotation. We demonstrate in a variety of experiments that our network is able to localize the discriminative image regions despite just being trained for solving classification task1.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Media Laboratory
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2016.319
