Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps

no code implementations • 23 Apr 2022 • Oren Barkan, Edan Hauon, Avi Caciularu, Ori Katz, Itzik Malkiel, Omri Armstrong, Noam Koenigstein

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks.

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

no code implementations • 2 Sep 2021 • Oren Barkan, Omri Armstrong, Amir Hertz, Avi Caciularu, Ori Katz, Itzik Malkiel, Noam Koenigstein

The algorithmic advantages of GAM are explained in detail, and validated empirically, where it is shown that GAM outperforms its alternatives across various tasks and datasets.

Classification

Robust Model Compression Using Deep Hypotheses

1 code implementation • 13 Mar 2021 • Omri Armstrong, Ran Gilad-Bachrach

This leads to our Compact Robust Estimated Median Belief Optimization (CREMBO) algorithm for robust model compression.

Binary Classification Knowledge Distillation +1