敵対的ドメイン適応による屋外ロボティクスの見た目変化への対応
Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
天候や季節による見た目の変化に頑健な機械学習のため、教師なしドメイン適応に敵対的手法を適用し、特徴量をドメイン間で揃えるフレームワークを開発。安定化のためのアブレーション研究を経て自動運転の自由空間セグメンテーションに応用した。
著者: Markus Wulfmeier, Alex Bewley, Ingmar Posner
分類: cs.RO, cs.LG
原文アブストラクト
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it will deliver degraded performance in application domains that underlie distributional shifts caused by these changes. Traditionally, this problem has been addressed via the collection of labelled data in multiple domains or by imposing priors on the type of shift between both domains. We frame the problem in the context of unsupervised domain adaptation and develop a framework for applying adversarial techniques to adapt popular, state-of-the-art network architectures with the additional objective to align features across domains. Moreover, as adversarial training is notoriously unstable, we first perform an extensive ablation study, adapting many techniques known to stabilise generative adversarial networks, and evaluate on a surrogate classification task with the same appearance change. The distilled insights are applied to the problem of free-space segmentation for motion planning in autonomous driving.
