Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset

11/16/2021

∙

In this paper we explore the influence of some frequently used Convolutional Neural Networks (CNNs), training settings, and training set structures, on Action Unit (AU) detection. Specifically, we first compare 10 different shallow and deep CNNs in AU detection. Second, we investigate how the different training settings (i.e. centering/normalizing the inputs, using different augmentation severities, and balancing the data) impact the performance in AU detection. Third, we explore the effect of increasing the number of labelled subjects and frames in the training set on the AU detection performance. These comparisons provide the research community with useful tips about the choice of different CNNs and training settings in AU detection. In our analysis, we use a large-scale naturalistic dataset, consisting of 55K videos captured in the wild. To the best of our knowledge, there is no work that had investigated the impact of such settings on a large-scale AU dataset.

READ FULL TEXT

Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset

Choose Settings Carefully: Comparing Action Unit detection at Different Settings Using a Large-Scale Dataset

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild

Convolutional Neural Networks for Automatic Meter Reading

Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?

The impact of training dataset size and ensemble inference strategies on head and neck auto-segmentation

Detection of gravitational waves using topological data analysis and convolutional neural network: An improved approach

Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset

Related Research

Choose Settings Carefully: Comparing Action Unit detection at Different Settings Using a Large-Scale Dataset

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild

Convolutional Neural Networks for Automatic Meter Reading

Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?

The impact of training dataset size and ensemble inference strategies on head and neck auto-segmentation

Detection of gravitational waves using topological data analysis and convolutional neural network: An improved approach