Paper ID: 2310.18585

Visual Explanations via Iterated Integrated Attributions

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. IIA employs iterative integration across the input image, the internal representations generated by the model, and their gradients, yielding precise and focused explanation maps. We demonstrate the effectiveness of IIA through comprehensive evaluations across various tasks, datasets, and network architectures. Our results showcase that IIA produces accurate explanation maps, outperforming other state-of-the-art explanation techniques.

Submitted: Oct 28, 2023