Ex Paucis Plura: Learning Affordance Segmentation from Very Few Examples

Johann Sawatzky, Martin Garbade, Juergen Gall

Abstract

While annotating objects in images is already time-consuming, annotating finer details like object parts or affordances of objects is even more tedious. Given the fact that large datasets with object annotations already exist, we address the question whether we can leverage such information to train a convolutional neural network for segmenting affordances or object parts from very few examples with finer annotations. To achieve this, we use a semantic alignment network to transfer the annotations from the small set of annotated examples to a large set of images with only coarse annotations at object level. We then train a convolutional neural network weakly supervised on the small annotated training set and the additional images with transferred labels. We evaluate our approach on the IIT-AFF and Pascal Parts dataset where our approach outperforms other weakly supervised approaches.
BibTeX
@inproceedings{sawatzky2018ex,
  author = {Johann Sawatzky and Martin Garbade and Juergen Gall},
  title = {{Ex Paucis Plura: Learning Affordance Segmentation from Very Few Examples}},
  booktitle = {GCPR},
  year = {2018},
  doi = {10.1007/978-3-030-12939-2\_13},
}

Loading related content...

Figure