Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs. Existing methods learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen perturbations at test time. To address this, we propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution, capable of modelling heavy-tailed distributions. We compare our model with a wide variety of state-of-the-art methods on various challenging tasks including unpaired image translation of natural images, using standard datasets, spanning autonomous driving, maps, facades, and also in medical imaging domain consisting of MRI. Experimental results demonstrate that our method exhibits stronger robustness towards unseen perturbations in test data. Code is released here: https://github.com/ExplainableML/UncertaintyAwareCycleConsistency.
翻译:为解决这一问题,我们建议一种基于不确定性常识通用适应循环一致性的新型概率方法(UGAC),该方法通过通用的高山分布,模拟重尾分布,来模拟每像素残留物,能够模拟重尾分布。我们将模型与各种具有挑战性的任务,包括自然图象的未剖面图像翻译、使用标准数据集、跨越自主驾驶、地图、外观,以及由MRI组成的医学成像领域的各种最新先进方法进行比较。实验结果显示,我们的方法在测试数据中表现出对不可见扰动的坚固性。 代码在这里发布: https://github.com/ExplainableML/UncertyCycleConsicent。