Robustness via Uncertainty-aware Cycle Consistency.

Annual Conference on Neural Information Processing Systems(2021)

引用 14|浏览18
暂无评分
摘要
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 spanning autonomous driving, maps, facades, and also in the 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.
更多
查看译文
关键词
robustness,cycle,uncertainty-aware
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要