ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Pérez
11/30/2018
cs.CV

Official code: valeoai/ADVENT (395 stars, last commit 2021-01-17).

Abstract

Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major challenge. In numerous real world applications, there is indeed a large gap between data distributions in train and test domains, which results in severe performance loss at run-time. In this work, we address the task of unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions. To this end, we propose two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively. We demonstrate state-of-the-art performance in semantic segmentation on two challenging "synthetic-2-real" set-ups and show that the approach can also be used for detection.

View on arXivView PDF

Code Implementations(1)

valeoai/ADVENTOfficial100%

Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

39571Python, DockerfileApr 4, 20195 years agoNOASSERTION

Similar Papers

Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation

87% match2023

Convolution-based Probability Gradient Loss for Semantic Segmentation

87% match1 repo22024

Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samples

86% match2023

FDA: Fourier Domain Adaptation for Semantic Segmentation

85% match1 repo5602020

Learning to Adapt Structured Output Space for Semantic Segmentation

85% match1 repo8572018

Adversarial Learning for Semi-Supervised Semantic Segmentation

84% match1 repo5072018

Cite this paper

@article{vu2018advent,
  title  = {ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation},
  author = {Tuan-Hung Vu and Himalaya Jain and Maxime Bucher and Matthieu Cord and Patrick Pérez},
  year   = {2018},
  eprint = {1811.12833},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1811.12833}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1811.12833.svg)](https://codeofpaper.com/paper/1811.12833)

Discussion