Robustness and Overfitting Behavior of Implicit Background Models

Abstract

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.

Publication
In IEEE International Conference on Image Processing
Charlie Lehman
Charlie Lehman
PhD Student

My research interests include robustness and explainability of deep vision models.

Related