基于惩罚约束的分割网络邻域感知校准方法
Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints
AI总结：
针对现有分割网络校准方法忽略像素空间结构的问题，提出基于logit等式约束的邻域感知校准方法NACL，可显式调控约束与惩罚权重，在多基准上实现更优校准且不影响判别力，具备模型无关性。
摘要：
确保深度神经网络输出可靠的置信度得分在关键决策系统中至关重要，尤其是在医疗等现实领域。近期关于深度分割网络校准的研究已取得显著进展，但这些方法深受分类任务进展的启发，通常仅利用单个像素的信息建模不确定性，忽略了目标对象的局部结构。实际上，只有近期提出的Spatially Varying Label Smoothing（空间变化标签平滑，SVLS）方法通过离散空间高斯核软化像素标签分配，考虑了跨类别的像素空间关系。本研究首先从约束优化的视角分析SVLS，证明其对周围像素的软类别比例施加了隐式约束。进一步分析表明，SVLS缺乏平衡约束贡献与主目标的机制，可能会阻碍优化过程。基于这些发现，我们提出NACL（Neighbor Aware CaLibration，邻域感知校准）——一种基于logit值等式约束的原理性简洁解决方案，可显式控制所施加的约束和惩罚权重，具备更高灵活性。在多种知名分割基准上的综合实验表明，该方法在不影响判别能力的前提下，实现了更优的校准性能。此外，消融实验实证证明了该方法的模型无关性，可用于训练各类深度分割网络。
英文摘要：
Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly in real-world domains such as healthcare. Recent literature on calibrating deep segmentation networks has resulted in substantial progress. Nevertheless, these approaches are strongly inspired by the advancements in classification tasks, and thus their uncertainty is usually modeled by leveraging the information of individual pixels, disregarding the local structure of the object of interest. Indeed, only the recent Spatially Varying Label Smoothing (SVLS) approach considers pixel spatial relationships across classes, 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 NACL (Neighbor Aware CaLibration), 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 wide variety of well-known segmentation benchmarks demonstrate the superior calibration performance of the proposed approach, without affecting its discriminative power. Furthermore, ablation studies empirically show the model agnostic nature of our approach, which can be used to train a wide span of deep segmentation networks.
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。
