Semantic Contours from Inverse Detectors

Bharath Hariharan, Pablo Arbeláez, Lubomir D. Bourdev, Subhransu Maji, Jitendra Malik

ICCV 2011 pp. 991-998

doi:10.1109/ICCV.2011.6126343 /iccv/2011/hariharan2011iccv-semantic/

Abstract

We study the challenging problem of localizing and classifying category-specific object contours in real world images. For this purpose, we present a simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours. We also provide a principled way of combining information from different part detectors and across categories. In order to study the problem and evaluate quantitatively our approach, we present a dataset of semantic exterior boundaries on more than 20, 000 object instances belonging to 20 categories, using the images from the VOC2011 PASCAL challenge [7].

PDF ICCV Semantic Scholar

Cite

Text

Hariharan et al. "Semantic Contours from Inverse Detectors." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126343

Markdown

[Hariharan et al. "Semantic Contours from Inverse Detectors." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/hariharan2011iccv-semantic/) doi:10.1109/ICCV.2011.6126343

BibTeX

@inproceedings{hariharan2011iccv-semantic,
  title     = {{Semantic Contours from Inverse Detectors}},
  author    = {Hariharan, Bharath and Arbeláez, Pablo and Bourdev, Lubomir D. and Maji, Subhransu and Malik, Jitendra},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {991-998},
  doi       = {10.1109/ICCV.2011.6126343},
  url       = {https://mlanthology.org/iccv/2011/hariharan2011iccv-semantic/}
}