Pixel-Wise Deep Learning for Contour Detection

Abstract

We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient implementation of multiscale convolutional neural networks (CNNs), to extract an informative feature vector for each pixel and uses an SVM classifier to accomplish contour detection. In the experiment of contour detection, we look into the effectiveness of combining per-pixel features from different CNN layers and verify their performance on BSDS500.

Cite

Text

Hwang and Liu. "Pixel-Wise Deep Learning for Contour Detection." International Conference on Learning Representations, 2015.

Markdown

[Hwang and Liu. "Pixel-Wise Deep Learning for Contour Detection." International Conference on Learning Representations, 2015.](https://mlanthology.org/iclr/2015/hwang2015iclr-pixel/)

BibTeX

@inproceedings{hwang2015iclr-pixel,
  title     = {{Pixel-Wise Deep Learning for Contour Detection}},
  author    = {Hwang, Jyh-Jing and Liu, Tyng-Luh},
  booktitle = {International Conference on Learning Representations},
  year      = {2015},
  url       = {https://mlanthology.org/iclr/2015/hwang2015iclr-pixel/}
}