Continual Unsupervised Domain Adaptation with Adversarial Learning

by   Joonhyuk Kim, et al.

Unsupervised Domain Adaptation (UDA) is essential for autonomous driving due to a lack of labeled real-world road images. Most of the existing UDA methods, however, have focused on a single-step domain adaptation (Synthetic-to-Real). These methods overlook a change in environments in the real world as time goes by. Thus, developing a domain adaptation method for sequentially changing target domains without catastrophic forgetting is required for real-world applications. To deal with the problem above, we propose Continual Unsupervised Domain Adaptation with Adversarial learning (CUDA^2) framework, which can generally be applicable to other UDA methods conducting adversarial learning. CUDA^2 framework generates a sub-memory, called Target-specific Memory (TM) for each new target domain guided by Double Hinge Adversarial (DHA) loss. TM prevents catastrophic forgetting by storing target-specific information, and DHA loss induces a synergy between the existing network and the expanded TM. To the best of our knowledge, we consider realistic autonomous driving scenarios (Synthetic-to-Real-to-Real) in UDA research for the first time. The model with our framework outperforms other state-of-the-art models under the same settings. Besides, extensive experiments are conducted as ablation studies for in-depth analysis.


SPIGAN: Privileged Adversarial Learning from Simulation

Deep Learning for Computer Vision depends mainly on the source of superv...

FRuDA: Framework for Distributed Adversarial Domain Adaptation

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapti...

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

Continual Machine Reading Comprehension aims to incrementally learn from...

Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving

While supervised detection and classification frameworks in autonomous d...

Unsupervised Domain Adaptation Meets Offline Recommender Learning

To construct a well-performing recommender offline, eliminating selectio...

f-Domain-Adversarial Learning: Theory and Algorithms

Unsupervised domain adaptation is used in many machine learning applicat...

Domain Adaptation Using Adversarial Learning for Autonomous Navigation

Autonomous navigation has become an increasingly popular machine learnin...