Home /

Research

Showing 265 - 270 / 897

Regularization with Latent Space Virtual Adversarial Training


Authors:  GenkiOsada, BudrulAhsan, RevotiPrasadBora....
Published date-11/26/2020
Tasks:  ImageClassification

Abstract: 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


Authors:  EmanueleBastianelli, AndreaVanzo, PawelSwietojanski....
Published date-11/26/2020
Tasks:  SpokenLanguageUnderstanding

Abstract: 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


Authors:  NicklasHansen, XiaolongWang....
Published date-11/26/2020
Tasks:  DataAugmentation

Abstract: 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


Authors:  BenedekFabian, ThomasEdlich, HélénaGaspar....
Published date-11/26/2020
Tasks:  DrugDiscovery, RepresentationLearning

Abstract: 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


Authors:  GiuseppeBoccignone, DonatelloConte, VittorioCuculo....
Published date-11/26/2020
Tasks:  Heartrateestimation, Photoplethysmography(PPG)

Abstract: 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


Authors:  HemantYadav, JanvijaySingh, AtulAnshumanSingh....
Published date-11/25/2020

Abstract: 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, …

Filter by

Categories

Tags