# FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions Source: [FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:37:02.192Z Authors: Sohyun Lee, Namyup Kim, Sungyeon Kim, Suha Kwak Published: 2024-07-18T12:07:02.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()