Abstract
Current advances in object recognition and scene understanding have been enabled by the availability of large number of labeled images. Similar advances in RGB-D image understanding are hampered by the current lack of large labeled datasets in this domain. We have a developed a new technique “cross-modal distillation” which enables us to transfer supervision from RGB to RGB-D datasets. We use representations learned from labeled RGB images as a supervisory signal to train representations for depth images, and observe a 6% relative gain in performance for object detection with RGB-D images, and a 20% relative improvement when only using the depth image.
Original language | English (US) |
---|---|
Pages (from-to) | 444-447 |
Number of pages | 4 |
Journal | Digest of Technical Papers - SID International Symposium |
Volume | 47 |
Issue number | 1 |
DOIs | |
State | Published - 2016 |
Externally published | Yes |
Event | 54th Annual SID Symposium, Seminar, and Exhibition 2016, Display Week 2016 - San Francisco, United States Duration: May 22 2016 → May 27 2016 |
Keywords
- RGB-D Scene Understanding
ASJC Scopus subject areas
- General Engineering