Itay Hubara

Itay Hubara

Director of AI at a stealth-mode startup. PhD from the Technion. Formerly Principal Engineer at Habana Labs/Intel. My research focuses on General LLM efficiency, Agentic Workflows, RAG, and HW-SW co-design. Contributor to MLPerf with over 10,000 citations.

Augment Your Batch: Improving Generalization Through Instance Repetition

Published in CVPR 2020, 2020

Recommended citation: Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, Daniel Soudry. (2020). "Augment Your Batch: Improving Generalization Through Instance Repetition." CVPR 2020. https://openaccess.thecvf.com/content_CVPR_2020/papers/Hoffer_Augment_Your_Batch_Improving_Generalization_Through_Instance_Repetition_CVPR_2020_paper.pdf

We propose to repeat instances within a batch with different data augmentations. This simple modification consistently improves generalization across various models and datasets.

Download paper here