提升医学图像翻译的不确定性估计，让模型更懂自己哪里没把握。
Uncertainty-Aware Regularization for Image-to-Image Translation
- 引入不确定感知正则化，利用参数先验优化不确定性预测
- 在噪声和伪影下仍能准确识别模型困难区域，重建质量更好
- 适合医疗图像分析中需要可信度评估的场景
深度网络中量化不确定性对可靠的实际应用至关重要。本文提出一种方法，改进医学图像到图像（I2I）翻译中的不确定性估计。模型融合了随机不确定性，并采用受简单先验启发的不确定感知正则化（UAR），以优化不确定性估计并提升重建质量。实验表明，通过利用参数上的简单先验，该方法能生成更鲁棒的不确定性图，精确指示网络遇到困难的位置，同时减少噪声干扰。UAR不仅提升了翻译性能，还改善了不确定性估计，尤其在存在噪声和伪影时表现更优。我们在两个医学影像数据集上验证了该方法的有效性，证明其能在熟悉区域保持高置信度，同时在新异或模糊场景中准确识别不确定性区域。
原文摘要 · Abstract (English)
The importance of quantifying uncertainty in deep networks has become paramount for reliable real-world applications. In this paper, we propose a method to improve uncertainty estimation in medical Image-to-Image (I2I) translation. Our model integrates aleatoric uncertainty and employs Uncertainty-Aware Regularization (UAR) inspired by simple priors to refine uncertainty estimates and enhance reconstruction quality. We show that by leveraging simple priors on parameters, our approach captures more robust uncertainty maps, effectively refining them to indicate precisely where the network encounters difficulties, while being less affected by noise. Our experiments demonstrate that UAR not only improves translation performance, but also provides better uncertainty estimations, particularly in the presence of noise and artifacts. We validate our approach using two medical imaging datasets, showcasing its effectiveness in maintaining high confidence in familiar regions while accurately identifying areas of uncertainty in novel/ambiguous scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。