Pith. sign in

REVIEW

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.09142 v2 pith:EF2GYUY2 submitted 2022-06-18 cs.SD eess.AS

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

classification cs.SD eess.AS
keywords lossnetworkredundancyfunctionreductiontrainingtwinsbest
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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% increase over a vanilla CNN 14 CCC of 0.647, which achieves a significant difference at the 95% confidence interval (2-tailed).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.