SpaCE-VAE: Sparse and Confident Explanations usingVariational Autoencoders
Year: 2025
Type: article
Abstract: In the field of explainable AI (XAI), a significant challenge lies in the evaluation of explanation methods. State-ofthe- art techniques identify the importance of input features (e.g., pixels) for the classification, based on untestable assumptions about the model. Lowering the intensity of pixels, identified as irrelevant, typically leads to a change in the predicted class. To address this, we propose SpaCEVAE, a Variational Autoencoder (VAE) designed to generate sparse, confident explanations that are inherently evaluable. SpaCE-VAE produces a sparse representation of an image, putting as many pixels as possible to black, such that the resulting image is still assigned to the same class as the original image (with high confidence).
Authors: Alexander Liu, Sibylle Hess
Institution: Eindhoven University of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7117883574