Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation
OPEN ACCESS
Loading...
Author / Producer
Date
2023
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Standard unsupervised domain adaptation methods adapt models from a source to a target domain using labeled source data and unlabeled target data jointly. In model adaptation, on the other hand, access to the labeled source data is prohibited, i.e., only the source-trained model and unlabeled target data are available. We investigate normal-to-adverse condition model adaptation for semantic segmentation, whereby image-level correspondences are available in the target domain. The target set consists of unlabeled pairs of adverse- and normalcondition street images taken at GNSS-matched locations. Our method—CMA—leverages such image pairs to learn condition-invariant features via contrastive learning. In particular, CMA encourages features in the embedding space to be grouped according to their condition-invariant semantic content and not according to the condition under which respective inputs are captured. To obtain accurate cross-domain semantic correspondences, we warp the normal image to the viewpoint of the adverse image and leverage warp-confidence scores to create robust, aggregated features. With this approach, we achieve state-of-the-art semantic segmentation performance for model adaptation on several normal-to-adverse adaptation benchmarks, such as ACDC and Dark Zurich. We also evaluate CMA on a newly procured adverse-condition generalization benchmark and report favorable results compared to standard unsupervised domain adaptation methods, despite the comparative handicap of CMA due to source data inaccessibility.
Permanent link
Publication status
published
External links
Editor
Book title
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Journal / series
Volume
Pages / Article No.
11344 - 11353
Publisher
IEEE
Event
19th IEEE/CVF International Conference on Computer Vision (ICCV 2023)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus)
Notes
Funding
Related publications and datasets
Is supplemented by: https://doi.org/10.3929/ethz-b-000626144