Redundancy Reduction Twins Network：一个多输出情感回归的训练框架
Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression
摘要：
在本文中，我们提出了Redundancy Reduction Twins Network（RRTN），这是一种冗余减少训练框架，通过测量同一网络的输出之间的互相关矩阵来最大限度地减少冗余，该网络提供了失真的样本版本，并使其尽可能接近单位矩阵。RRTN还应用了一个新的损失函数，巴洛双胞胎损失函数，以帮助最大限度地提高从样本的不同失真版本获得的表示的相似性。然而，由于损失的分布可能会导致网络的性能波动，我们还建议使用约束不确定性权重损失（RUWL）或联合训练来确定损失函数的最佳权重。我们使用所提出的方法在CNN14上的最佳方法在ExVo多任务开发集上获得了0.678的CCC超过情绪回归，比0.647的香草CNN 14 CCC增加了4.8%，这在95%置信区间（双尾）实现了显著差异。
英文摘要：
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).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
