FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913435267104768 |
|---|---|
| author | Lee, Sohyun Kim, Namyup Kim, Sungyeon Kwak, Suha |
| author_facet | Lee, Sohyun Kim, Namyup Kim, Sungyeon Kwak, Suha |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13437 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions Lee, Sohyun Kim, Namyup Kim, Sungyeon Kwak, Suha Computer Vision and Pattern Recognition 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. |
| title | FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.13437 |