BTSeg: Barlow Twins Regularization for Domain Adaptation in Semantic Segmentation
This addresses the problem of robust perception for autonomous vehicles in varying weather, representing an incremental improvement in weakly-supervised domain adaptation.
The paper tackles domain adaptation for semantic segmentation under adverse weather conditions without extra labeled data, achieving state-of-the-art performance on the ACG benchmark and ACDC dataset.
We introduce BTSeg (Barlow Twins regularized Segmentation), an innovative, semi-supervised training approach enhancing semantic segmentation models in order to effectively tackle adverse weather conditions without requiring additional labeled training data. Images captured at similar locations but under varying adverse conditions are regarded as manifold representation of the same scene, thereby enabling the model to conceptualize its understanding of the environment. BTSeg shows cutting-edge performance for the new challenging ACG benchmark and sets a new state-of-the-art for weakly-supervised domain adaptation for the ACDC dataset. To support further research, we have made our code publicly available at https://github.com/fraunhoferhhi/BTSeg .