BTSeg: Barlow Twins Regularization for Domain Adaptation in Semantic Segmentation

31 Aug 2023  ·  Johannes Künzel, Anna Hilsmann, Peter Eisert ·

Semantic image segmentation is particularly vital for the advancement of autonomous vehicle technologies. However, this domain faces substantial challenges under adverse conditions like rain or darkness, which remain underrepresented in most datasets. The generation of additional training data for these scenarios is not only costly but also fraught with potential inaccuracies, largely attributable to the aleatoric uncertainty inherent in such conditions. We introduce BTSeg, an innovative, semi-supervised training approach enhancing semantic segmentation models in order to effectively handle a range of adverse conditions without requiring the creation of extensive new datasets. BTSeg employs a novel application of the Barlow Twins loss, a concept borrowed from unsupervised learning. The original Barlow Twins approach uses stochastic augmentations in order to learn useful representations from unlabeled data without the need for external labels. In our approach, we regard images captured at identical locations but under varying adverse conditions as manifold representation of the same scene (which could be interpreted as "natural augmentations"), thereby enabling the model to conceptualize its understanding of the environment. We evaluate our approach on the ACDC dataset, where it performs favorably when compared to the current state-of-the-art methods, while also being simpler to implement and train. For the new challenging ACG benchmark it shows cutting-edge performance, demonstrating its robustness and generalization capabilities. We will make the code publicly available post-acceptance.

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods