论文标题
局部温度缩放以进行概率校准
Local Temperature Scaling for Probability Calibration
论文作者
论文摘要
对于语义分割，标签概率通常是未校准的，因为它们通常仅是分割任务的副产品。联合（IOU）和骰子得分的交集通常被用作分割成功的标准，而与标签概率相关的指标并未经常探索。但是，已经研究了概率校准方法，这些方法与实验观察到的误差相匹配。这些方法主要集中于分类任务，而不是语义细分。因此，我们提出了一种基于学习的校准方法，该方法侧重于多标签语义分割。具体而言，我们采用卷积神经网络来预测局部温度值的概率校准。我们方法的一个优点是，它不会改变预测准确性，因此可以作为后处理步骤进行校准。可可，CAMVID和LPBA40数据集的实验表明，对于一系列不同的指标，校准性能提高了。我们还展示了从磁共振图像中进行多ATLAS脑分割的方法的良好性能。
For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmentation success, while metrics related to label probabilities are not often explored. However, probability calibration approaches have been studied, which match probability outputs with experimentally observed errors. These approaches mainly focus on classification tasks, but not on semantic segmentation. Thus, we propose a learning-based calibration method that focuses on multi-label semantic segmentation. Specifically, we adopt a convolutional neural network to predict local temperature values for probability calibration. One advantage of our approach is that it does not change prediction accuracy, hence allowing for calibration as a post-processing step. Experiments on the COCO, CamVid, and LPBA40 datasets demonstrate improved calibration performance for a range of different metrics. We also demonstrate the good performance of our method for multi-atlas brain segmentation from magnetic resonance images.
