Enhancing Interpretability and Gaining Insights into Robustness in Vision-Language Models Through Core and Spurious Feature Detection via Counterfactuals

Lecture notes in computer science 2026

View at publisher

Authors: Anjon Basak, Adrienne J. Raglin

DOI: 10.1007/978-3-032-13184-3_8

Cited by: 0

References: 22

Fields of Study & Subjects

Multimodal Machine Learning Applications Explainable Artificial Intelligence (XAI) Generative Adversarial Networks and Image Synthesis

References 22