Abstract
Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs.
Original language | English (US) |
---|---|
Title of host publication | 2017 26th International Conference on Computer Communications and Networks, ICCCN 2017 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781509029914 |
DOIs | |
State | Published - Sep 14 2017 |
Event | 26th International Conference on Computer Communications and Networks, ICCCN 2017 - Vancouver, Canada Duration: Jul 31 2017 → Aug 3 2017 |
Other
Other | 26th International Conference on Computer Communications and Networks, ICCCN 2017 |
---|---|
Country/Territory | Canada |
City | Vancouver |
Period | 7/31/17 → 8/3/17 |
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Networks and Communications
- Software
- Management of Technology and Innovation
- Information Systems and Management
- Safety, Risk, Reliability and Quality
- Media Technology
- Control and Optimization