Tal Rosenwein — accepted AI-conference papers

2024

Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework

Eliya Segev, Maya Alroy, Ronen Katsir, Noam Wies, Ayana Shenhav, Yael Sapir Ben-Oren +5

ICLR 2024poster

Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It learns the alignments between the input and output sequences by marginalizing over the perfect alignments (that yield the ground truth), at the expense of the impe…

Cited by 2 Source ↗PDF ↗Scholar ↗

2016

Learning a Metric Embedding for Face Recognition using the Multibatch Method

Oren Tadmor, Tal Rosenwein, Shai Shalev-Shwartz, Yonatan Wexler, Amnon Shashua

NeurIPS 2016poster

This work is motivated by the engineering task of achieving a near state-of-the-art face recognition on a minimal computing budget running on an embedded system. Our main technical contribution centers around a novel training method, called Multibatch, for similarity learning, i.e., for the task of…

Cited by 53 Source ↗PDF ↗Scholar ↗