Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression

06/18/2022
by   Xin Jing, et al.
0

In this paper, we propose the Redundancy Reduction Twins Network (RRTN), a redundancy reduction training framework that minimizes redundancy by measuring the cross-correlation matrix between the outputs of the same network fed with distorted versions of a sample and bringing it as close to the identity matrix as possible. RRTN also applies a new loss function, the Barlow Twins loss function, to help maximize the similarity of representations obtained from different distorted versions of a sample. However, as the distribution of losses can cause performance fluctuations in the network, we also propose the use of a Restrained Uncertainty Weight Loss (RUWL) or joint training to identify the best weights for the loss function. Our best approach on CNN14 with the proposed methodology obtains a CCC over emotion regression of 0.678 on the ExVo Multi-task dev set, a 4.8 0.647, which achieves a significant difference at the 95 (2-tailed).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/24/2023

Multi-stage feature decorrelation constraints for improving CNN classification performance

For the convolutional neural network (CNN) used for pattern classificati...
research
09/04/2018

End-to-end Multimodal Emotion and Gender Recognition with Dynamic Weights of Joint Loss

Multi-task learning (MTL) is one of the method for improving generalizab...
research
09/04/2018

End-to-end Multimodal Emotion and Gender Recognition with Dynamic Joint Loss Weights

Multi-task learning is a method for improving the generalizability of mu...
research
11/02/2020

Multimodal Continuous Emotion Recognition using Deep Multi-Task Learning with Correlation Loss

In this study, we focus on continuous emotion recognition using body mot...
research
03/30/2022

Region of Interest focused MRI to Synthetic CT Translation using Regression and Classification Multi-task Network

In this work, we present a method for synthetic CT (sCT) generation from...
research
10/03/2013

Multivariate regression and fit function uncertainty

This article describes a multivariate polynomial regression method where...
research
11/09/2022

A Diffeomorphic Flow-based Variational Framework for Multi-speaker Emotion Conversion

This paper introduces a new framework for non-parallel emotion conversio...

Please sign up or login with your details

Forgot password? Click here to reset