Work

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Year: 2019

Type: conference-paper

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.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr.2019.00262

Authors: Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Perez

Institution: Sorbonne Université

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W2902727564

FWCI: 51.31

Cites: 54

Cited by: 1,535

Related to: 10