Corpus ID: 233169077

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

@article{Borse2021InverseFormAL,
  title={InverseForm: A Loss Function for Structured Boundary-Aware Segmentation},
  author={S. Borse and Ying Wang and Yizhe Zhang and F. Porikli},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.02745}
}

• S. Borse, Ying Wang, +1 author F. Porikli
• Published 2021
• Computer Science
• ArXiv

We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations and allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity. We analyze the quantitative and… Expand

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed