Sorry, you need to enable JavaScript to visit this website.


Citation Author(s):
Erik Brorsson, Knut Åkesson, Lennart Svensson, Kristofer Bengtsson
Submitted by:
Erik Brorsson
Last updated:
2 February 2024 - 2:46am
Document Type:
Supplementary material

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training methods are susceptible to misclassified pseudo-labels resulting from erroneous predictions. Since certain classes are typically associated with less reliable predictions in UDA, reducing the impact of such pseudo-labels without skewing the training towards some classes is notoriously difficult.
To this end, we propose an extensive cut-and-paste strategy (ECAP) to leverage reliable pseudo-labels through data augmentation.
Specifically, ECAP maintains a memory bank of pseudo-labeled target samples throughout training and cut-and-pastes the most confident ones onto the current training batch. We implement ECAP on top of the recent method MIC and boost its performance on two synthetic-to-real domain adaptation benchmarks. Notably, MIC+ECAP reaches an unprecedented performance of 69.1 mIoU on the Synthia→Cityscapes benchmark. Our code is available at

0 users have voted: