# Sensitivity analysis of image classification models using generalized polynomial chaos

Source: [Sensitivity analysis of image classification models using generalized polynomial chaos](<https://www.sota2.com/research/paper/68fa79a01e209131cea7e845>)

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

Data updated: 2026-02-05T05:00:14.183Z

Authors: Lukas Bahr, Lucas Po{\\ss}ner, Konstantin Weise, Sophie Gr\\"oger, R\\"udiger Daub

Published: 2025-06-23T15:22:31.000Z

## Abstract

Integrating advanced communication protocols in production has accelerated the adoption of data-driven predictive quality methods, notably machine learning (ML) models. However, ML models in image classification often face significant uncertainties arising from model, data, and domain shifts. These uncertainties lead to overconfidence in the classification model's output. To better understand these models, sensitivity analysis can help to analyze the relative influence of input parameters on the output. This work investigates the sensitivity of image classification models used for predictive quality. We propose modeling the distributional domain shifts of inputs with random variables and quantifying their impact on the model's outputs using Sobol indices computed via generalized polynomial chaos (GPC). This approach is validated through a case study involving a welding defect classification problem, utilizing a fine-tuned ResNet18 model and an emblem classification model used in BMW Group production facilities.

## 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/2506.18751>)

[PDF](<https://arxiv.org/pdf/2506.18751.pdf>)