Page - 15 - in Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
Image of the Page - 15 -
Text of the Page - 15 -
One Shot Learning of
Scene Categories via Feature
Trajectory Transfer
Roland Kwitt1,
Sebastian Hegenbart1, Marc Niethammer2
1 University of Salzburg,
Austria;
2
University of North Carolina, Chapel Hill, NC,
USA
Abstract
The appearance of (outdoor) scenes changes considerably with the strength of certain transient
attributes, such as ``rainy'', ``dark'' or ``sunny''. Obviously, this also affects the representation of
an image in feature space, e.g., as activations at a certain CNN layer, and consequently impacts
scene recognition performance. In this work, we investigate the variability in these transient
attributes as a rich source of information for studying how image representations change as a
function of attribute strength. In particular, we leverage a recently introduced dataset with fine
grain annotations to estimate feature trajectories for a collection of transient attributes and then
show how these trajectories can be transferred to new image representations. This enables us to
synthesize new data along the transferred trajectories with respect to the dimensions of the space
spanned by the transient attributes. Applicability of this concept is demonstrated on the problem of
one shot scene recognition. We show that data synthesized via feature trajectory transfer
considerably boosts recognition performance, (1) with respect to baselines and (2) in combination
with state of
the art approaches in one shot learning.
15
Proceedings
OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
- Title
- Proceedings
- Subtitle
- OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
- Authors
- Peter M. Roth
- Kurt Niel
- Publisher
- Verlag der Technischen Universität Graz
- Location
- Wels
- Date
- 2017
- Language
- English
- License
- CC BY 4.0
- ISBN
- 978-3-85125-527-0
- Size
- 21.0 x 29.7 cm
- Pages
- 248
- Keywords
- Tagungsband
- Categories
- International
- Tagungsbände