# Robustness and Overfitting Behavior of Implicit Background Models

Source: [Robustness and Overfitting Behavior of Implicit Background Models](<https://www.sota2.com/research/paper/68fa68341e209131cea1ac2f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:32:00.581Z

Authors: Shirley Liu, Charles Lehman, Ghassan AlRegib

Published: 2020-08-21T05:08:33.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2008.09306>)

[PDF](<https://arxiv.org/pdf/2008.09306.pdf>)