FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions
This addresses the problem of semantic segmentation in real-world adverse conditions for applications like autonomous driving, though it is incremental as it builds on existing source-free domain adaptation methods.
The paper tackles robust semantic segmentation under adverse conditions when labeled normal images are unavailable during training, proposing FREST, a feature restoration framework for source-free domain adaptation that achieved state-of-the-art results on ACDC and RobotCar benchmarks.
Robust semantic segmentation under adverse conditions is crucial in real-world applications. To address this challenging task in practical scenarios where labeled normal condition images are not accessible in training, we propose FREST, a novel feature restoration framework for source-free domain adaptation (SFDA) of semantic segmentation to adverse conditions. FREST alternates two steps: (1) learning the condition embedding space that only separates the condition information from the features and (2) restoring features of adverse condition images on the learned condition embedding space. By alternating these two steps, FREST gradually restores features where the effect of adverse conditions is reduced. FREST achieved a state of the art on two public benchmarks (i.e., ACDC and RobotCar) for SFDA to adverse conditions. Moreover, it shows superior generalization ability on unseen datasets.