43 citations · 47 across the 9 of their papers we have counts for
7 papers · 1 filter
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
Yehonatan Elisha, Oren Barkan, Noam Koenigstein
Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features…
Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
Yehonatan Elisha, Seffi Cohen, Oren Barkan +1
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 use…
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…
Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond
Oren Barkan, Tal Reiss, Jonathan Weill +4
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different…