77 citations · 168 across the 15 of their papers we have counts for
5 papers · 1 filter
No Pairs Left Behind: Improving Metric Learning with Regularized Triplet Objective
A. Ali Heydari, Naghmeh Rezaei, Daniel J. McDuff +1
We propose a novel formulation of the triplet objective function that improves metric learning without additional sample mining or overhead costs. Our approach aims to explicitly r…
Contrastive Learning of Global-Local Video Representations
Shuang Ma, Zhaoyang Zeng, Daniel McDuff +1
Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific t…
Active Contrastive Learning of Audio-Visual Video Representations
Shuang Ma, Zhaoyang Zeng, Daniel McDuff +1
Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different…
Multi-Reference Neural TTS Stylization with Adversarial Cycle Consistency
Matt Whitehill, Shuang Ma, Daniel McDuff +1
Current multi-reference style transfer models for Text-to-Speech (TTS) perform sub-optimally on disjoints datasets, where one dataset contains only a single style class for one of…
Identifying Bias in AI using Simulation
Daniel McDuff, Roger Cheng, Ashish Kapoor
Machine learned models exhibit bias, often because the datasets used to train them are biased. This presents a serious problem for the deployment of such technology, as the resulti…