This work presents a two-staged, unsupervised domain adaptation process for semantic segmentation models by combining a self-training and self-supervision strategy. Self-training (i. e., training a model on self-inferred pseudo-labels) yields competitive results for domain adaptation in recent research. However, self-training depends on high-quality pseudo-labels. On the other hand, self-supervision trains the model on a surrogate task and improves its performance on the target domain without further prerequisites. Therefore, our approach improves the model's performance on the target domain with a novel surrogate task. To that, we continuously determine class centroids of the feature representations in the network’s pre-logit layer on the source domain. Our surrogate task clusters the pre-logit feature representations on the target domain regarding these class centroids during both training stages. After the first stage, the resulting model delivers improved pseudo-labels for the additional self-training in the second stage. We evaluate our method on two different domain adaptions, a real-world domain change from Cityscapes to the Berkeley Deep Drive dataset and a synthetic to real-world domain change from GTA5 to the Cityscapes dataset. For the real-world domain change, the evaluation shows a significant improvement of the model from 46% mIoU to 54% mIoU on the target domain. For the synthetic to real-world domain change, we achieve an improvement from 38.8% to 46.42% on the real-world target domain


    Access

    Download


    Export, share and cite



    Title :

    Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation


    Contributors:

    Conference:

    2021 ; Nagoya, Japan



    Publication date :

    2021-07-01


    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Adversarial Self-Training with Domain Mask for Semantic Segmentation

    Hsin, Hsien-Kai / Chiu, Hsiao-Chien / Lin, Chun-Chen et al. | IEEE | 2019


    Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

    Michieli, Umberto / Biasetton, Matteo / Agresti, Gianluca et al. | IEEE | 2020


    Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision

    Meletis, Panagiotis / Romijnders, Rob / Dubbelman, Gijs | IEEE | 2019


    Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation

    Zhang, Xiaohong / Chen, Yi / Shen, Ziyi et al. | IEEE | 2022