ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Code

• github.com/valeoai/ADVENT
  OfficialIn paperpytorch★ 0
• github.com/thuml/Transfer-Learning-Library
  pytorch★ 3,889
• github.com/yuan-zm/dgt-st
  pytorch★ 35
• github.com/attm/tensorflow_advent
  tf★ 0

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.

Tasks

Benchmark Results

Reproductions