TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Djoumessi, Kerol, Berens, Philipp
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916063322570752
author Djoumessi, Kerol
Berens, Philipp
author_facet Djoumessi, Kerol
Berens, Philipp
contents Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized from the original weights. The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability
format Preprint
id arxiv_https___arxiv_org_abs_2603_26885
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs
Djoumessi, Kerol
Berens, Philipp
Computer Vision and Pattern Recognition
Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized from the original weights. The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability
title TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.26885