Oren Barkan

Robust mixture models for anomaly detection

2016

We propose robust density estimation in a low dimensional space for anomaly detection. The outline of the method is as follows: first a low dimensional representation of the original data is learnt. Then, a robust …

Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations

2025 · arXiv (Cornell University)

Saliency maps are widely used for visual explanations in deep learning, but a fundamental lack of consensus persists regarding their intended purpose and alignment with diverse user queries. This ambiguity hinders the effective evaluation and …