Restricted Receptive Fields for Face Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ozturk, Kagan, Bhatta, Aman, Wu, Haiyu, Flynn, Patrick, Bowyer, Kevin W.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917258445455360
author Ozturk, Kagan
Bhatta, Aman
Wu, Haiyu
Flynn, Patrick
Bowyer, Kevin W.
author_facet Ozturk, Kagan
Bhatta, Aman
Wu, Haiyu
Flynn, Patrick
Bowyer, Kevin W.
contents Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpretability is to assign importance to individual pixels using post-hoc methods. Although they are widely used to explain black-box models, their fidelity to the model's actual reasoning is uncertain due to the lack of reliable evaluation metrics. This limitation motivates an alternative approach, which is to design models whose decision processes are inherently interpretable. To this end, we propose a face similarity metric that breaks down global similarity into contributions from restricted receptive fields. Our method defines the similarity between two face images as the sum of patch-level similarity scores, providing a locally additive explanation without relying on post-hoc analysis. We show that the proposed approach achieves competitive verification performance even with patches as small as 28x28 within 112x112 face images, and surpasses state-of-the-art methods when using 56x56 patches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Restricted Receptive Fields for Face Verification
Ozturk, Kagan
Bhatta, Aman
Wu, Haiyu
Flynn, Patrick
Bowyer, Kevin W.
Computer Vision and Pattern Recognition
Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpretability is to assign importance to individual pixels using post-hoc methods. Although they are widely used to explain black-box models, their fidelity to the model's actual reasoning is uncertain due to the lack of reliable evaluation metrics. This limitation motivates an alternative approach, which is to design models whose decision processes are inherently interpretable. To this end, we propose a face similarity metric that breaks down global similarity into contributions from restricted receptive fields. Our method defines the similarity between two face images as the sum of patch-level similarity scores, providing a locally additive explanation without relying on post-hoc analysis. We show that the proposed approach achieves competitive verification performance even with patches as small as 28x28 within 112x112 face images, and surpasses state-of-the-art methods when using 56x56 patches.
title Restricted Receptive Fields for Face Verification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.10753