CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars

TL;DR

This paper introduces CONDA, a continual unsupervised domain adaptation method for semantic segmentation in self-driving cars that adapts to new data without needing access to previous training data, addressing privacy and practicality issues.

Contribution

The paper proposes a novel continual unsupervised domain adaptation approach that prevents catastrophic forgetting without accessing prior data, using a Bijective Maximum Likelihood loss.

Findings

CONDA outperforms existing methods on benchmark datasets.

It effectively prevents catastrophic forgetting.

The approach maintains high segmentation accuracy over time.

Abstract

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the segmentation models may encounter new data that have not been seen yet. Also, the previous data training of segmentation models may be inaccessible due to privacy problems. Therefore, to address these problems, in this work, we propose a Continual Unsupervised Domain Adaptation (CONDA) approach that allows the model to continuously learn and adapt with respect to the presence of the new data. Moreover, our proposed approach is designed without the requirement of accessing previous training data. To avoid the catastrophic forgetting problem and maintain the performance of the segmentation models, we present a novel Bijective Maximum Likelihood loss to impose the constraint of predicted segmentation distribution shifts. The experimental results on the benchmark of continual unsupervised domain adaptation have shown the advanced performance of the proposed CONDA method.