论文标题
除了无监督域适应的确定性翻译之外
Beyond Deterministic Translation for Unsupervised Domain Adaptation
论文作者
论文摘要
在这项工作中，我们挑战了在无监督域适应（UDA）中使用一对一映射（“翻译”）（UDA）之间的一对一映射（“翻译”）的常见方法。取而代之的是，我们依靠随机翻译来捕获固有的翻译歧义。这使我们能够（i）通过在同一源图像上生成多个输出来训练更准确的目标网络，利用准确的翻译和数据增强以获得外观可变性，（ii）通过在单个目标图像和（III II II III）范围内的多种目标网络上划分源网络的预测来为目标数据提供稳健的伪标记，以实现目标数据，以实现目标数据。翻译。我们报告了对最近的基线的改进，从而导致了两个具有挑战性的语义细分基准的最新UDA结果。我们的代码可在https://github.com/elchiou/beyond-deterministic-translation-for-uda上找到。
In this work we challenge the common approach of using a one-to-one mapping ('translation') between the source and target domains in unsupervised domain adaptation (UDA). Instead, we rely on stochastic translation to capture inherent translation ambiguities. This allows us to (i) train more accurate target networks by generating multiple outputs conditioned on the same source image, leveraging both accurate translation and data augmentation for appearance variability, (ii) impute robust pseudo-labels for the target data by averaging the predictions of a source network on multiple translated versions of a single target image and (iii) train and ensemble diverse networks in the target domain by modulating the degree of stochasticity in the translations. We report improvements over strong recent baselines, leading to state-of-the-art UDA results on two challenging semantic segmentation benchmarks. Our code is available at https://github.com/elchiou/Beyond-deterministic-translation-for-UDA.
