论文标题
隐性背景模型的鲁棒性和过度拟合行为
Robustness and Overfitting Behavior of Implicit Background Models
论文作者
论文摘要
在本文中，我们研究了通过隐式背景估计（SCRIBE）修改的图像分类模型的过度拟合行为，该模型将它们转换为弱监督的分割模型，这些模型可提供空间域可视化，而不会影响性能。使用分割掩模，我们得出了不需要测试标签的过度检测准则。此外，我们评估模型性能，校准和分割面罩的变化，将数据增强作为过度拟合量度和对各种扭曲的图像进行测试。
In this paper, we examine the overfitting behavior of image classification models modified with Implicit Background Estimation (SCrIBE), which transforms them into weakly supervised segmentation models that provide spatial domain visualizations without affecting performance. Using the segmentation masks, we derive an overfit detection criterion that does not require testing labels. In addition, we assess the change in model performance, calibration, and segmentation masks after applying data augmentations as overfitting reduction measures and testing on various types of distorted images.
