Instance Segmentation of Indoor Scenes Using a Coverage Loss

Abstract

A major limitation of existing models for semantic segmentation is the inability to identify individual instances of the same class: when labeling pixels with only semantic classes, a set of pixels with the same label could represent a single object or ten. In this work, we introduce a model to perform both semantic and instance segmentation simultaneously. We introduce a new higher-order loss function that directly minimizes the coverage metric and evaluate a variety of region features, including those from a convolutional network. We apply our model to the NYU Depth V2 dataset, obtaining state of the art results.

Cite

Text

Silberman et al. "Instance Segmentation of Indoor Scenes Using a Coverage Loss." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10590-1_40

Markdown

[Silberman et al. "Instance Segmentation of Indoor Scenes Using a Coverage Loss." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/silberman2014eccv-instance/) doi:10.1007/978-3-319-10590-1_40

BibTeX

@inproceedings{silberman2014eccv-instance,
  title     = {{Instance Segmentation of Indoor Scenes Using a Coverage Loss}},
  author    = {Silberman, Nathan and Sontag, David A. and Fergus, Rob},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {616-631},
  doi       = {10.1007/978-3-319-10590-1_40},
  url       = {https://mlanthology.org/eccv/2014/silberman2014eccv-instance/}
}