Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Adhikari, Sayanta, Kumar, Rishav, Mopuri, Konda Reddy, Pachamuthu, Rajalakshmi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929576791244800
author Adhikari, Sayanta
Kumar, Rishav
Mopuri, Konda Reddy
Pachamuthu, Rajalakshmi
author_facet Adhikari, Sayanta
Kumar, Rishav
Mopuri, Konda Reddy
Pachamuthu, Rajalakshmi
contents Contextual information plays a critical role in object recognition models within computer vision, where changes in context can significantly affect accuracy, underscoring models' dependence on contextual cues. This study investigates how context manipulation influences both model accuracy and feature attribution, providing insights into the reliance of object recognition models on contextual information as understood through the lens of feature attribution methods. We employ a range of feature attribution techniques to decipher the reliance of deep neural networks on context in object recognition tasks. Using the ImageNet-9 and our curated ImageNet-CS datasets, we conduct experiments to evaluate the impact of contextual variations, analyzed through feature attribution methods. Our findings reveal several key insights: (a) Correctly classified images predominantly emphasize object volume attribution over context volume attribution. (b) The dependence on context remains relatively stable across different context modifications, irrespective of classification accuracy. (c) Context change exerts a more pronounced effect on model performance than Context perturbations. (d) Surprisingly, context attribution in `no-information' scenarios is non-trivial. Our research moves beyond traditional methods by assessing the implications of broad-level modifications on object recognition, either in the object or its context.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02833
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition
Adhikari, Sayanta
Kumar, Rishav
Mopuri, Konda Reddy
Pachamuthu, Rajalakshmi
Computer Vision and Pattern Recognition
I.4.m; I.2.10
Contextual information plays a critical role in object recognition models within computer vision, where changes in context can significantly affect accuracy, underscoring models' dependence on contextual cues. This study investigates how context manipulation influences both model accuracy and feature attribution, providing insights into the reliance of object recognition models on contextual information as understood through the lens of feature attribution methods. We employ a range of feature attribution techniques to decipher the reliance of deep neural networks on context in object recognition tasks. Using the ImageNet-9 and our curated ImageNet-CS datasets, we conduct experiments to evaluate the impact of contextual variations, analyzed through feature attribution methods. Our findings reveal several key insights: (a) Correctly classified images predominantly emphasize object volume attribution over context volume attribution. (b) The dependence on context remains relatively stable across different context modifications, irrespective of classification accuracy. (c) Context change exerts a more pronounced effect on model performance than Context perturbations. (d) Surprisingly, context attribution in `no-information' scenarios is non-trivial. Our research moves beyond traditional methods by assessing the implications of broad-level modifications on object recognition, either in the object or its context.
title Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition
topic Computer Vision and Pattern Recognition
I.4.m; I.2.10
url https://arxiv.org/abs/2411.02833