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

• URL: http://arxiv.org/abs/2603.26885v1
• Date: Fri, 27 Mar 2026 18:02:32 GMT
• Title: TTE-CAM: Built-in Class Activation Maps for Test-Time Explainability in Pretrained Black-Box CNNs
• Abstract summary: Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings.<n>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, from the original weights.<n>The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively.
• Score: 5.70867735038766
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• UNBOX: Unveiling Black-box visual models with Natural-language [50.433977345786055]
  We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints.<n>We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses, and slice-discovery auditing.
  arXiv  Detail & Related papers  (2026-03-09T17:16:39Z)
• Soft-CAM: Making black box models self-explainable for high-stakes decisions [6.635611625764804]
  Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance.<n>Most explanation methods rely on post-hoc attribution, approximating the decision-making process of already trained black-box models.<n>We introduce SoftCAM, a straightforward yet effective approach that makes standard CNN architectures inherently interpretable.
  arXiv  Detail & Related papers  (2025-05-23T11:15:21Z)
• A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Disease Detection from Retinal Fundus Images [5.079347310071244]
  We introduce an interpretable-by-design hybrid fully convolutional CNN-Transformer architecture for retinal disease detection.<n>Our model achieves state-of-the-art predictive performance compared to black-box and interpretable models.
  arXiv  Detail & Related papers  (2025-04-11T12:15:22Z)
• Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification [3.9626211140865464]
  Convolutional Neural Networks (CNNs) have seen significant performance improvements in recent years.<n>However, due to their size and complexity, they function as black-boxes, leading to transparency concerns.<n>This paper introduces a novel post-hoc explainability framework, Visual-TCAV, which aims to bridge the gap between these methods.
  arXiv  Detail & Related papers  (2024-11-08T16:52:52Z)
• Video Prediction Transformers without Recurrence or Convolution [65.93130697098658]
  We propose PredFormer, a framework entirely based on Gated Transformers.<n>We provide a comprehensive analysis of 3D Attention in the context of video prediction.<n>The significant improvements in both accuracy and efficiency highlight the potential of PredFormer.
  arXiv  Detail & Related papers  (2024-10-07T03:52:06Z)
• Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable? [8.391254800873599]
  We introduce a method to perform concept-based interventions on pretrained neural networks, which are not interpretable by design. We formalise the notion of intervenability as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes.
  arXiv  Detail & Related papers  (2024-01-24T16:02:14Z)
• An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification [55.28171619580959]
  This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting.
  arXiv  Detail & Related papers  (2023-07-25T11:51:14Z)
• Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers [33.82339346293966]
  Convolutional Neural Network (CNN) has achieved excellent performance in the classification task. It is widely known that CNN is deemed as a 'black-box', which is hard for understanding the prediction mechanism. We propose the first completely automatic model diagnosing and treating tool, termed as Model Doctor.
  arXiv  Detail & Related papers  (2021-12-09T14:05:00Z)
• Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study [116.05514467222544]
  Generative adversarial networks (GANs) nowadays are capable of producing images of incredible realism. One concern raised is whether the state-of-the-art GAN's learned distribution still suffers from mode collapse. This paper explores to diagnose GAN intra-mode collapse and calibrate that, in a novel black-box setting.
  arXiv  Detail & Related papers  (2021-07-23T06:03:55Z)
• Regularizing Explanations in Bayesian Convolutional Neural Networks [0.4538232180176148]
  We propose a new explanation regularization method compatible with Bayesian inference.<n>Our method improves predictive performance when models overfit on spurious features or are uncertain of which features to focus on.
  arXiv  Detail & Related papers  (2021-04-29T13:59:21Z)
• BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks [65.2021953284622]
  We study robustness of CNNs against white-box and black-box adversarial attacks. Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
  arXiv  Detail & Related papers  (2021-03-14T20:43:19Z)
• Neural Networks with Recurrent Generative Feedback [61.90658210112138]
  We instantiate this design on convolutional neural networks (CNNs) In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
  arXiv  Detail & Related papers  (2020-07-17T19:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.