ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Perez; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2517-2526

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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Vu_2019_CVPR,
author = {Vu, Tuan-Hung and Jain, Himalaya and Bucher, Maxime and Cord, Matthieu and Perez, Patrick},
title = {ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}