# Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation Source: [Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:38:22.399Z Authors: Yangsong Zhang, Subhankar Roy, Hongtao Lu, Elisa Ricci, St\\'ephane Lathuili\\\`ere Published: 2022-10-04T13:03:17.000Z ## Abstract In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions. To address MTDA, we propose a self-training strategy that employs pseudo-labels to induce cooperation among multiple domain-specific classifiers. We employ feature stylization as an efficient way to generate image views that forms an integral part of self-training. Additionally, to prevent the network from overfitting to noisy pseudo-labels, we devise a rectification strategy that leverages the predictions from different classifiers to estimate the quality of pseudo-labels. Our extensive experiments on numerous settings, based on four different semantic segmentation datasets, validate the effectiveness of the proposed self-training strategy and show that our method outperforms state-of-the-art MTDA approaches. Code available at: https://github.com/Mael-zys/CoaST ## 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]()