Visualizing Object Detection Features
Name
11263_2016_884_ReferencePDF.pdf
Size
8.53 MB
Format
Adobe PDF
Checksum (MD5)
f1ff9124dd1144f96a60bf4650cf12e9
Author(s)
Pirsiavash, Hamed
Malisiewicz, Tomasz
Vondrick, Carl Martin
Khosla, Aditya
Torralba, Antonio
Date Issued
March 2016
Journal
International Journal of Computer Vision
Publisher
Springer US
Citation
Vondrick, Carl, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, and Antonio Torralba. “Visualizing Object Detection Features.” Int J Comput Vis 119, no. 2 (March 1, 2016): 145–158.
Version
Author's final manuscript
Abstract
We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector’s failures. For example, when we visualize the features for high scoring false alarms, we discovered that, although they are clearly wrong in image space, they often look deceptively similar to true positives in feature space. This result suggests that many of these false alarms are caused by our choice of feature space, and supports that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors without improving the features. By visualizing feature spaces, we can gain a more intuitive understanding of recognition systems.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11263-016-0884-7
