4 papers
BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation
Oren Barkan, Yehonatan Elisha, Jonathan Weill +1
Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information through baseline representations. T…
Visual Explanations via Iterated Integrated Attributions
Oren Barkan, Yehonatan Elisha, Yuval Asher +2
We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models. IIA employs iterative integration across the input image, th…
Deep Integrated Explanations
Oren Barkan, Yehonatan Elisha, Jonathan Weill +3
This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the interme…
Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Models
Oren Barkan, Yuval Asher, Amit Eshel +2
We present Learning to Explain (LTX), a model-agnostic framework designed for providing post-hoc explanations for vision models. The LTX framework introduces an "explainer" model t…