43 citations · 67 across the 9 of their papers we have counts for
11 papers
Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps
Oren Barkan, Edan Hauon, Avi Caciularu +4
Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks. As this revolution continues, the ability to explain model predictions has b…
Caption Enriched Samples for Improving Hateful Memes Detection
Efrat Blaier, Itzik Malkiel, Lior Wolf
The recently introduced hateful meme challenge demonstrates the difficulty of determining whether a meme is hateful or not. Specifically, both unimodal language models and multimod…
GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
Oren Barkan, Omri Armstrong, Amir Hertz +4
We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activatio…
Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation
Itzik Malkiel, Sangtae Ahn, Valentina Taviani +3
Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling muc…
RecoBERT: A Catalog Language Model for Text-Based Recommendations
Itzik Malkiel, Oren Barkan, Avi Caciularu +3
Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety…
MTAdam: Automatic Balancing of Multiple Training Loss Terms
Itzik Malkiel, Lior Wolf
When training neural models, it is common to combine multiple loss terms. The balancing of these terms requires considerable human effort and is computationally demanding. Moreover…