Article

Quantitative Attributions with Counterfactuals

2024-12-02

Abstract excerpt

We address the problem of explaining the decision process of deep neural network classifiers on images, which is of particular importance in biomedical datasets where class-relevant differences are not always obvious to a human observer. Our proposed solution, termed quantitative attribution with counterfactuals (QuAC), generates visual explanations that highlight class-relevant differences by attributing the clas...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 2da829ba-257a-5c69-bd8a-1650e46317fd
DOI: 10.1101/2024.11.26.625505

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Quantitative Attributions with CounterfactualsDOI 10.1101/2024.11.26.625505Read

Training Calibration-based Counterfactual Explainers for Deep Learning Models in Medical Image AnalysisSemantic proximity Read

VPNet: A Unified Explainable Classification Framework Using Probabilistic Circuits and Foundation ModelsSemantic proximity Read

Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilizationSemantic proximity Read

A Framework for Generating Counterfactual Explanations to Explain Black-Box ModelsSemantic proximity Read

Sensitivity based model agnostic scalable explanations of deep learningSemantic proximity Read

Quantifying Interpretation Reproducibility in Vision Transformer Models with TAVACSemantic proximity Read

Validation of neuron activation patterns for deep learning models in oculomicsSemantic proximity Read

Towards Trustworthy Breast Cancer Diagnosis: A Comparative Explainability Stability Study of DenseNet121 and Vision TransformersSemantic proximity Read

TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning ModelsSemantic proximity Read

Reliable interpretability of biology-inspired deep neural networksSemantic proximity Read

Comparing Brain-Score and ImageNet performance with responses to the scintillating grid illusionSemantic proximity Read

Explainable Deep Learning for TEM-Based Classification of Carbon Nanoparticles: A ResNet50 Transfer Learning ApproachSemantic proximity Read