Visualizing Object Detection Features
| dc.contributor.author | Vondrick, Carl | |
| dc.contributor.author | Khosla, Aditya | |
| dc.contributor.author | Pirsiavash, Hamed | |
| dc.contributor.author | Malisiewicz, Tomasz | |
| dc.contributor.author | Torralba, Antonio | |
| dc.date.accessioned | 2019-07-03T15:41:28Z | |
| dc.date.available | 2019-07-03T15:41:28Z | |
| dc.date.issued | 2016-03-01 | |
| dc.description.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. | en_US |
| dc.description.sponsorship | Funding was provided by a NSF GRFP and Google Ph.D. Fellowship to CV, a Facebook fellowship to AK, and a Google research award, ONR MURI N000141010933 and NSF Career Award No. 0747120 to AT. | en_US |
| dc.description.uri | https://link.springer.com/article/10.1007/s11263-016-0884-7 | en_US |
| dc.format.extent | 14 pages | en_US |
| dc.genre | journal articles preprints | en_US |
| dc.identifier | doi:10.13016/m24gwl-xrfc | |
| dc.identifier.citation | Vondrick, C., Khosla, A., Pirsiavash, H. et al. Int J Comput Vis (2016) 119: 145. https://doi.org/10.1007/s11263-016-0884-7 | en_US |
| dc.identifier.uri | https://doi.org/10.1007/s11263-016-0884-7 | |
| dc.identifier.uri | http://hdl.handle.net/11603/14337 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Springer US | en_US |
| dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
| dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
| dc.relation.ispartof | UMBC Faculty Collection | |
| dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | |
| dc.subject | Feature visualization | en_US |
| dc.subject | Visual recognition | en_US |
| dc.subject | Object detection | en_US |
| dc.title | Visualizing Object Detection Features | en_US |
| dc.type | Text | en_US |