ML Anthology

Objects as Context for Detecting Their Semantic Parts

Abel Gonzalez-Garcia, Davide Modolo, Vittorio Ferrari
CVPR 2018
doi:10.1109/CVPR.2018.00722 /cvpr/2018/gonzalezgarcia2018cvpr-objects/

Abstract

We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.

PDF CVPR Semantic Scholar

Cite

Text

Gonzalez-Garcia et al. "Objects as Context for Detecting Their Semantic Parts." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00722

Markdown

[Gonzalez-Garcia et al. "Objects as Context for Detecting Their Semantic Parts." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/gonzalezgarcia2018cvpr-objects/) doi:10.1109/CVPR.2018.00722

BibTeX

@inproceedings{gonzalezgarcia2018cvpr-objects,
  title     = {{Objects as Context for Detecting Their Semantic Parts}},
  author    = {Gonzalez-Garcia, Abel and Modolo, Davide and Ferrari, Vittorio},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00722},
  url       = {https://mlanthology.org/cvpr/2018/gonzalezgarcia2018cvpr-objects/}
}