Soft-CAM: Making black box models self-explainable for medical image analysis

Kerol Djoumessi, Philipp Berens

Keywords: ElasticNet, Self-explainable models, Convolutional Neural Networks, Class Activation Maps, Attribution maps

TL;DR: we introduce SoftCAM, a straightforward yet effective approach that makes standard CNN architectures inherently interpretable.

Abstract: Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance. However, most explanation methods rely on post-hoc attribution, approximating the decision-making process of already trained black-box models. These methods are often sensitive, unreliable, and fail to reflect true model reasoning, limiting their trustworthiness in critical applications. In this work, we introduce SoftCAM, a straightforward yet effective approach that makes standard CNN architectures inherently interpretable. By removing the global average pooling layer and replacing the fully connected classification layer with a convolution-based class evidence layer, SoftCAM preserves spatial information and produces explicit class activation maps that form the basis of the model's predictions. Evaluated on three medical datasets spanning three imaging modalities, SoftCAM maintains classification performance while significantly improving both the qualitative and quantitative explanation compared to existing post-hoc methods. The code is available at \url{https://github.com/kdjoumessi/SoftCAM}.

Primary Subject Area: Interpretability and Explainable AI

Secondary Subject Area: Detection and Diagnosis

Registration Requirement: Yes

Reproducibility: https://github.com/kdjoumessi/SoftCAM

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 39