Home /
Research
Showing 265 - 270 / 897
Regularization with Latent Space Virtual Adversarial Training
GenkiOsada, BudrulAhsan, RevotiPrasadBora....
Published date-11/26/2020
ImageClassification
Virtual Adversarial Training (VAT) has shown impressive results among recently developed regularization methods called consistency regularization. VAT utilizes adversarial samples, generated by injecting perturbation in the input space, for training …
SLURP: A Spoken Language Understanding Resource Package
EmanueleBastianelli, AndreaVanzo, PawelSwietojanski....
Published date-11/26/2020
SpokenLanguageUnderstanding
Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. However, publicly available SLU resources are limited. In …
Generalization in Reinforcement Learning by Soft Data Augmentation
NicklasHansen, XiaolongWang....
Published date-11/26/2020
DataAugmentation
Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during …
Molecular representation learning with language models and domain-relevant auxiliary tasks
BenedekFabian, ThomasEdlich, HélénaGaspar....
Published date-11/26/2020
DrugDiscovery, RepresentationLearning
We apply a Transformer architecture, specifically BERT, to learn flexible and high quality molecular representations for drug discovery problems. We study the impact of using different combinations of self-supervised tasks …
An Open Framework for Remote-PPG Methods and their Assessment
GiuseppeBoccignone, DonatelloConte, VittorioCuculo....
Published date-11/26/2020
Heartrateestimation, Photoplethysmography(PPG)
This paper presents a comprehensive framework for studying methods of pulse rate estimation relying on remote photoplethysmography (rPPG). There has been a remarkable development of rPPG techniques in recent years, …
De-STT: De-entaglement of unwanted Nuisances and Biases in Speech to Text System using Adversarial Forgetting
HemantYadav, JanvijaySingh, AtulAnshumanSingh....
Published date-11/25/2020
Training robust Speech to Text (STT) system require "tens of thousand" of hours of data. Variability present in the dataset, in the form of unwanted nuisances (noise) and biases (accent, …