ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Autor:	Vu, Tuan-Hung, Jain, Himalaya, Bucher, Maxime, Cord, Matthieu, Pérez, Patrick
Rok vydání:	2018
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted in CVPR'19. Code is available at https://github.com/valeoai/ADVENT
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1811.12833 Zobrazit plný text záznamu View this record from Arxiv