Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance

TL;DR

This paper introduces a probabilistic framework and an algorithm for unsupervised domain adaptation of posteriors, specifically improving semantic segmentation in real-world surveillance where domain conditions vary and are unknown.

Contribution

The paper proposes a novel algorithm for many-to-infinity domain adaptation that combines source models and a domain discriminator to adapt posteriors without supervision.

Findings

Effective semantic segmentation in surveillance scenarios

Algorithm works with convex combinations of source domain measures

Code is publicly available for reproducibility

Abstract

Various tasks encountered in real-world surveillance can be addressed by determining posteriors (e.g. by Bayesian inference or machine learning), based on which critical decisions must be taken. However, the surveillance domain (acquisition device, operating conditions, etc.) is often unknown, which prevents any possibility of scene-specific optimization. In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors. Our proposed algorithm is applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains. It makes use of source models and a domain discriminator model trained off-line to compute posteriors adapted on the fly to the target domain. Finally, we show the effectiveness of our algorithm for the task of semantic segmentation in real-world surveillance. The code is publicly available at https://github.com/rvandeghen/MDA.