信任你的邻居：基于惩罚约束的模型校准方法
Trust your neighbours: Penalty-based constraints for model calibration
AI总结：
本文针对深度分割网络校准中忽略局部结构的问题，从约束优化角度分析 SVLS 的不足，提出基于 logit 等式约束的校准方法，可显式控制约束与惩罚权重，并在多个分割基准上验证了其优越性。
摘要：
在关键决策系统中，尤其是在医学领域，确保深度网络输出可靠的置信度分数至关重要。尽管近年来关于深度分割网络校准的研究取得了显著进展，但其不确定性通常通过利用单个像素的信息来建模，这忽略了感兴趣目标的局部结构。特别是，只有最近的 Spatially Varying Label Smoothing (SVLS) 方法通过使用离散空间高斯核软化像素标签分配来解决这一问题。在本工作中，我们首先提出对 SVLS 的约束优化视角，并证明它对周围像素的软类别比例施加了隐式约束。此外，我们的分析表明，SVLS 缺乏一种机制来平衡该约束与主要目标之间的贡献，这可能阻碍优化过程。基于这些观察，我们提出了一种基于 logit 值等式约束的原则性且简单的解决方案，该方案能够同时显式控制所施加的约束和惩罚的权重，从而提供更大的灵活性。在多种知名分割基准上的综合实验证明了所提方法的优越性能。
英文摘要：
Ensuring reliable confidence scores from deep networks is of pivotal importance in critical decision-making systems, notably in the medical domain. While recent literature on calibrating deep segmentation networks has led to significant progress, their uncertainty is usually modeled by leveraging the information of individual pixels, which disregards the local structure of the object of interest. In particular, only the recent Spatially Varying Label Smoothing (SVLS) approach addresses this issue by softening the pixel label assignments with a discrete spatial Gaussian kernel. In this work, we first present a constrained optimization perspective of SVLS and demonstrate that it enforces an implicit constraint on soft class proportions of surrounding pixels. Furthermore, our analysis shows that SVLS lacks a mechanism to balance the contribution of the constraint with the primary objective, potentially hindering the optimization process. Based on these observations, we propose a principled and simple solution based on equality constraints on the logit values, which enables to control explicitly both the enforced constraint and the weight of the penalty, offering more flexibility. Comprehensive experiments on a variety of well-known segmentation benchmarks demonstrate the superior performance of the proposed approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
