Weakly Supervised Affordance Detection

Johann Sawatzky, Abhilash Srikantha, Juergen Gall

CVPR 2017

doi:10.1109/CVPR.2017.552 /cvpr/2017/sawatzky2017cvpr-weakly/

Abstract

Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances. Since parts of an object can have multiple affordances, we address this by a convo- lutional neural network for multilabel affordance segmen- tation. We also propose an approach to train the network from very few keypoint annotations. Our approach achieves a higher affordance detection accuracy than other weakly supervised methods that also rely on keypoint annotations or image annotations as weak supervision.

PDF CVPR Semantic Scholar

Cite

Text

Sawatzky et al. "Weakly Supervised Affordance Detection." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.552

Markdown

[Sawatzky et al. "Weakly Supervised Affordance Detection." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/sawatzky2017cvpr-weakly/) doi:10.1109/CVPR.2017.552

BibTeX

@inproceedings{sawatzky2017cvpr-weakly,
  title     = {{Weakly Supervised Affordance Detection}},
  author    = {Sawatzky, Johann and Srikantha, Abhilash and Gall, Juergen},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.552},
  url       = {https://mlanthology.org/cvpr/2017/sawatzky2017cvpr-weakly/}
}