Related papers: Counterfactual Explanations for Medical Image Clas…

Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that this default choice, not the diffusion architecture, is the dominant constraint on…

In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an explanation method that uses examples, has attracted attention. However, it has been pointed out that…

Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form ``if an input datapoint were $x'$ instead of $x$, then an ML…

Automated grading of Knee Osteoarthritis (KOA) from radiographs is challenged by significant inter-observer variability and the limited robustness of deep learning models, particularly near critical decision boundaries. To address these…

Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown promise in disentangling latent representations, existing…

Counterfactual explanations (CFEs) guide users on how to adjust inputs to machine learning models to achieve desired outputs. While existing research primarily addresses static scenarios, real-world applications often involve data or model…

Generative AI has received substantial attention in recent years due to its ability to synthesize data that closely resembles the original data source. While Generative Adversarial Networks (GANs) have provided innovative approaches for…

Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although…

Post-hoc explanation methods for machine learning models have been widely used to support decision-making. One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a…

Counterfactual explanations enhance the interpretability of deep learning models in medical imaging, yet adapting them to 3D CT scans poses challenges due to volumetric complexity and resource demands. We extend the Latent Shift…

Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model's original decision. The generated samples can act as a recommendation for end-users to achieve their desired…

Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction. However, these approaches neglect the causal relationships…

Counterfactual explanations have substantially increased in popularity in the past few years as a useful human-centric way of understanding individual black-box model predictions. While several properties desired of high-quality…

Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output. A valid counterfactual explanation…

Medical image segmentation is crucial for clinical diagnosis and treatment planning. Traditional methods typically produce a single segmentation mask, failing to capture inherent uncertainty. Recent generative models enable the creation of…

Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored. We aim to close this gap by proposing a unified probabilistic model for…

We leverage diffusion models to study the robustness-performance tradeoff of robust classifiers. Our approach introduces a simple, pretrained diffusion method to generate low-norm counterfactual examples (CEs): semantically altered data…

Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare by assisting decision-makers to answer ''what-iF'' questions. Existing causal inference approaches typically consider regular, discrete-time…