# ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation Source: [ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:45:34.560Z Authors: Erik Brorsson, Knut {\\AA}kesson, Lennart Svensson, Kristofer Bengtsson Published: 2024-03-06T17:06:07.000Z ## Abstract 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 https://github.com/ErikBrorsson/ECAP. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()