Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kerol Djoumessi, Philipp Berens

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. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability

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

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. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability

Paper Structure

This paper contains 8 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Datasets.
  4. Method.
  5. Post-hoc baseline.
  6. Evaluation metrics.
  7. Results
  8. Discussion and Conclusion

Figures (1)

  • Figure 1: Qualitative explanations comparison. The first column shows a DR fundus with clinical annotations (green markers) and a pneumonia CXR with ground-truth bounding boxes (green). Columns 2-6 show post-hoc saliency maps; the last column shows TTE-CAM explanations. CXR scores indicate activation precision.