PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pohland, Sara, Tomlin, Claire
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918278399524864
author Pohland, Sara
Tomlin, Claire
author_facet Pohland, Sara
Tomlin, Claire
contents Convolutional neural networks (CNNs) are extremely popular and effective for image classification tasks but tend to be overly confident in their predictions. Various works have sought to quantify uncertainty associated with these models, detect out-of-distribution (OOD) inputs, or identify anomalous regions in an image, but limited work has sought to develop a holistic approach that can accurately estimate perception model confidence across various sources of uncertainty. We develop a probabilistic and reconstruction-based competency estimation (PaRCE) method and compare it to existing approaches for uncertainty quantification and OOD detection. We find that our method can best distinguish between correctly classified, misclassified, and OOD samples with anomalous regions, as well as between samples with visual image modifications resulting in high, medium, and low prediction accuracy. We describe how to extend our approach for anomaly localization tasks and demonstrate the ability of our approach to distinguish between regions in an image that are familiar to the perception model from those that are unfamiliar. We find that our method generates interpretable scores that most reliably capture a holistic notion of perception model confidence.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification
Pohland, Sara
Tomlin, Claire
Computer Vision and Pattern Recognition
Machine Learning
Convolutional neural networks (CNNs) are extremely popular and effective for image classification tasks but tend to be overly confident in their predictions. Various works have sought to quantify uncertainty associated with these models, detect out-of-distribution (OOD) inputs, or identify anomalous regions in an image, but limited work has sought to develop a holistic approach that can accurately estimate perception model confidence across various sources of uncertainty. We develop a probabilistic and reconstruction-based competency estimation (PaRCE) method and compare it to existing approaches for uncertainty quantification and OOD detection. We find that our method can best distinguish between correctly classified, misclassified, and OOD samples with anomalous regions, as well as between samples with visual image modifications resulting in high, medium, and low prediction accuracy. We describe how to extend our approach for anomaly localization tasks and demonstrate the ability of our approach to distinguish between regions in an image that are familiar to the perception model from those that are unfamiliar. We find that our method generates interpretable scores that most reliably capture a holistic notion of perception model confidence.
title PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.16715