TTE-CAM: Built-in Class Activation Maps for Test-Time Explainability in Pretrained Black-Box CNNs

Kerol Djoumessi, Philipp Berens

Keywords: Test-time explainability, Built-in CAMs, Mechanistic faithfulness, CNNs.

TL;DR: In this work, we introduce a straightforward test-time framework that transforms pretrained black-box CNNs into self-explainable models by replacing the classification head with a convolution-based layer initialized from the original weights.

Registration Requirement: Yes

Abstract: 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.

Reproducibility: https://github.com/kdjoumessi/Test-Time-Explainability

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 9