318 citations · 825 across the 71 of their papers we have counts for
6 papers · 1 filter
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
Vivek Ramanujan, Pavan Kumar Anasosalu Vasu, Ali Farhadi +2
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the…
Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition
Ting-Yao Hu, Mohammadreza Armandpour, Ashish Shrivastava +3
With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthe…
Data Incubation -- Synthesizing Missing Data for Handwriting Recognition
Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala +4
In this paper, we demonstrate how a generative model can be used to build a better recognizer through the control of content and style. We are building an online handwriting recogn…
Token Pooling in Vision Transformers
Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan +3
Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing me…
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Jen-Hao Rick Chang, Ashish Shrivastava, Hema Swetha Koppula +2
Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in diff…
Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
Pavan Kumar Anasosalu Vasu, Shreyas Saxena, Oncel Tuzel
Recent works have shown that deep neural networks benefit from multi-task learning by learning a shared representation across several related tasks. However, performance of such sy…