Visual Explanations via Iterated Integrated Attributions

1 code implementation • ICCV 2023 • Oren Barkan, Yehonatan Elisha, Yuval Asher, Amit Eshel, Noam Koenigstein

We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models.

Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Models

1 code implementation • 25 Oct 2023 • Oren Barkan, Yuval Asher, Amit Eshel, Yehonatan Elisha, Noam Koenigstein

We present Learning to Explain (LTX), a model-agnostic framework designed for providing post-hoc explanations for vision models.

counterfactual

Deep Integrated Explanations

1 code implementation • 23 Oct 2023 • Oren Barkan, Yehonatan Elisha, Jonathan Weill, Yuval Asher, Amit Eshel, Noam Koenigstein

This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models.