Learning to Localize Little Landmarks
http://vision.cs.uiuc.edu/projects/litland/
Learning to Localize, Little Landmarks

People
An algorithm to automatically learn to detect landmarks in a image specific learned order.
Abstract
We interact everyday with tiny objects such as the door handle of a car or the
light switch in a room. These little landmarks are barely visible and hard to
localize in images. We describe a method to find such landmarks by finding a
sequence of latent landmarks, each with a prediction model. Each latent
landmark predicts the next in sequence, and the last localizes the target
landmark. For example, to find the door handle of a car, our method learns to
start with a latent landmark near the wheel, as it is globally distinctive;
subsequent latent landmarks use the context from the earlier ones to get
closer to the target. Our method is supervised solely by the location of the
little landmark and displays strong performance on more difficult variants of
established tasks and on two new tasks.
Paper
![]() |
Paper: CVPR 2016 Pdf (3.6 MB)
Citation Saurabh Singh, Derek Hoiem and David Forsyth. Learning to Localize Little Landmarks . In Computer Vision and Pattern Recognition (2016). |
BibTeX
@inproceedings{Singh2016litland, author = {Saurabh Singh and Derek Hoiem and David Forsyth}, title = {Learning to Localize Little Landmarks}, booktitle={Computer Vision and Pattern Recognition}, year = {2016}, url = {http://vision.cs.illinois.edu/projects/litland/} }
Code
Coming soon.
Data
Car Door Handle Dataset. (Please see the README in the
zip file for details)
Light Switch Dataset. (Please see the README in the zip file for details)
Light Switch Dataset. (Please see the README in the zip file for details)