Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations

Although precision, recall, and other common metrics can provide a useful window into the performance of an object detection model, they lack a deeper view of the model’s decision process. Regardless of the quality of the training data and process, the features that an object detection model learns...

Full description

Saved in:
Bibliographic Details
Main Authors: Lynn Vonderhaar, Timothy Elvira, Omar Ochoa
Format: Article
Language:English
Published: LibraryPress@UF 2025-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/138922
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321668115169280
author Lynn Vonderhaar
Timothy Elvira
Omar Ochoa
author_facet Lynn Vonderhaar
Timothy Elvira
Omar Ochoa
author_sort Lynn Vonderhaar
collection DOAJ
description Although precision, recall, and other common metrics can provide a useful window into the performance of an object detection model, they lack a deeper view of the model’s decision process. Regardless of the quality of the training data and process, the features that an object detection model learns cannot be guaranteed. A model may learn a relationship between certain background context, i.e., scene level objects, and the presence of the labeled classes. Furthermore, standard performance metrics would not identify this phenomenon. This paper presents a black box explainability method for additional verification of object detection models by finding the impact of scene level objects on the identification of the classes within the image. By comparing the mean Average Precision (mAP) of a model on test data with and without certain scene level objects, the contributions of these objects to the model’s performance becomes clearer. This work presents two experiments to test the method. The experiment results provide quantitative explanations of the object detection model’s decision process, enabling a deeper understanding of the model’s performance.
format Article
id doaj-art-1b0a82c669c244bca78c70f5f058cfef
institution Kabale University
issn 2334-0754
2334-0762
language English
publishDate 2025-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-1b0a82c669c244bca78c70f5f058cfef2025-08-20T03:49:41ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622025-05-0138110.32473/flairs.38.1.138922Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative ExplanationsLynn Vonderhaar0Timothy Elvira1Omar Ochoa2Embry-Riddle Aeronautical UniversityEmbry-Riddle Aeronautical UniversityEmbry-Riddle Aeronautical UniversityAlthough precision, recall, and other common metrics can provide a useful window into the performance of an object detection model, they lack a deeper view of the model’s decision process. Regardless of the quality of the training data and process, the features that an object detection model learns cannot be guaranteed. A model may learn a relationship between certain background context, i.e., scene level objects, and the presence of the labeled classes. Furthermore, standard performance metrics would not identify this phenomenon. This paper presents a black box explainability method for additional verification of object detection models by finding the impact of scene level objects on the identification of the classes within the image. By comparing the mean Average Precision (mAP) of a model on test data with and without certain scene level objects, the contributions of these objects to the model’s performance becomes clearer. This work presents two experiments to test the method. The experiment results provide quantitative explanations of the object detection model’s decision process, enabling a deeper understanding of the model’s performance. https://journals.flvc.org/FLAIRS/article/view/138922ExplainabilityMachine LearningBlack Box ModelScene Level ObjectsContext
spellingShingle Lynn Vonderhaar
Timothy Elvira
Omar Ochoa
Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
Proceedings of the International Florida Artificial Intelligence Research Society Conference
Explainability
Machine Learning
Black Box Model
Scene Level Objects
Context
title Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
title_full Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
title_fullStr Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
title_full_unstemmed Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
title_short Measuring the Impact of Scene Level Objects: A Novel Method for Quantitative Explanations
title_sort measuring the impact of scene level objects a novel method for quantitative explanations
topic Explainability
Machine Learning
Black Box Model
Scene Level Objects
Context
url https://journals.flvc.org/FLAIRS/article/view/138922
work_keys_str_mv AT lynnvonderhaar measuringtheimpactofscenelevelobjectsanovelmethodforquantitativeexplanations
AT timothyelvira measuringtheimpactofscenelevelobjectsanovelmethodforquantitativeexplanations
AT omarochoa measuringtheimpactofscenelevelobjectsanovelmethodforquantitativeexplanations