---
markdown_generated_at: "2026-10-14"
title: "InverseForm: A Loss Function for Structured Boundary-Aware Segmentation"
url: "https://www.qualcomm.com/research/artificial-intelligence/papers-with-code/paper-2"
description: "InverseForm allows for capturing boundary transformations with consistent and significant performance improvement on segmentation backbone models."
canonicalUrl: "https://www.qualcomm.com/research/artificial-intelligence/papers-with-code/paper-2"
---

# InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

PAPER 2

Shubhankar Borse (Qualcomm AI Research),
Ying Wang (formerly Qualcomm AI Research),
Yizhe Zhang (formerly Qualcomm AI Research),
Fatih Porikli (Qualcomm AI Research)

CVPR 2021 oral

![](https://s7d1.scene7.com/is/image/dmqualcommprod/papers-w-code-2_0?$QC_Responsive$&fmt=png-alpha)

## Summary

The research introduces the InverseForm framework for creating better feature maps for semantic segmentation tasks. InverseForm allows for capturing boundary transformations with consistent and significant performance improvement on segmentation backbone models. This is all achieved without increasing their size and computational complexity.

[![](https://s7d1.scene7.com/is/image/dmqualcommprod/document-icon-v2_2?$QC_Responsive$&fmt=png-alpha) Paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Borse_InverseForm_A_Loss_Function_for_Structured_Boundary-Aware_Segmentation_CVPR_2021_paper.pdf)

[![](https://s7d1.scene7.com/is/image/dmqualcommprod/code-icon_2?$QC_Responsive$&fmt=png-alpha) Code](https://github.com/Qualcomm-AI-research/InverseForm)

## Citation

If you find our work useful for your research, please cite:
*@inproceedings{borse2021inverseform, title={InverseForm: A Loss Function for Structured Boundary-Aware Segmentation}, author={Borse, Shubhankar and Wang, Ying and Zhang, Yizhe and Porikli, Fatih}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2021}}*

![](https://s7d1.scene7.com/is/image/dmqualcommprod/inverseform?$QC_Responsive$&fmt=png-alpha)

InverseForm applied for semantic segmentation, accurately classifying and precisely segmenting objects. Raw video obtained from Cityscapes Benchmark: [https://www.cityscapes-dataset.com/](https://www.cityscapes-dataset.com/).

## Results

All models trained using InverseForm loss consistently improve compared to their baselines and produce scores on par with state-of-the-art results.

## Looking for more papers with code?

[View all papers](https://www.qualcomm.com/research/artificial-intelligence/papers-with-code)

\* Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.