Corpus ID: 221139695

Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!

  title={Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!},
  author={Maryam Matin and Matias Valdenegro-Toro},
Facial emotion recognition is the task to classify human emotions in face images. It is a difficult task due to high aleatoric uncertainty and visual ambiguity. A large part of the literature aims to show progress by increasing accuracy on this task, but this ignores the inherent uncertainty and ambiguity in the task. In this paper we show that Bayesian Neural Networks, as approximated using MC-Dropout, MC-DropConnect, or an Ensemble, are able to model the aleatoric uncertainty in facial… Expand
1 Citations
The VVAD-LRS3 Dataset for Visual Voice Activity Detection
This work created a large scale dataset called the VVAD-LRS3 dataset, derived by automatic annotations from the LRS3 datasets, which contains over 44K samples, over three times the next competitive dataset (WildVVAD). Expand


Emotion recognition in the wild using deep neural networks and Bayesian classifiers
This work presents a solution based on a novel combination of deep neural networks and Bayesian classifiers for group emotion recognition in the wild, significantly outperforming the competition baseline. Expand
Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks
Experiments on Ensembles with Shared Representations based on convolutional networks suggest that ESRs reduce the remaining residual generalization error on the AffectNet and FER+ datasets, reach human-level performance, and outperform state-of-the-art methods on facial expression recognition in the wild using emotion and affect concepts. Expand
Image based Static Facial Expression Recognition with Multiple Deep Network Learning
This work reports the proposed image based static facial expression recognition method for the Emotion Recognition in the Wild Challenge (EmotiW) 2015, and presents two schemes for learning the ensemble weights of the network responses by minimizing the log likelihood loss and the hinge loss. Expand
A Brief Review of Facial Emotion Recognition Based on Visual Information
A brief review of researches in the field of FER conducted over the past decades, focusing on an up-to-date hybrid deep-learning approach combining a convolutional neural network for the spatial features of an individual frame and long short-term memory for temporal features of consecutive frames. Expand
Training deep networks for facial expression recognition with crowd-sourced label distribution
This paper shows how to learn a deep convolutional neural network (DCNN) from noisy labels, using facial expression recognition as an example, and compares four different approaches to utilizing the multiple labels. Expand
Local Learning With Deep and Handcrafted Features for Facial Expression Recognition
We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieveExpand
Human Uncertainty Makes Classification More Robust
It is shown that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on this dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks. Expand
Deep Face Recognition
It is shown how a very large scale dataset can be assembled by a combination of automation and human in the loop, and the trade off between data purity and time is discussed. Expand
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
A large-scale benchmark of existing state-of-the-art methods on classification problems and the effect of dataset shift on accuracy and calibration is presented, finding that traditional post-hoc calibration does indeed fall short, as do several other previous methods. Expand
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand