BReG-NeXt: Facial Affect Computing Using Adaptive Residual Networks With Bounded Gradient

1 code implementation • 18 Apr 2020 • Behzad Hasani, Pooran Singh Negi, Mohammad H. Mahoor

We conducted comprehensive experiments on the categorical and dimensional models of affect on the challenging in-the-wild databases of AffectNet, FER2013, and Affect-in-Wild.

Facial Expression Recognition Facial Expression Recognition (FER)

Leveraging Class Similarity to Improve Deep Neural Network Robustness

no code implementations • 23 Dec 2018 • Pooran Singh Negi, David Chan, Mohammad Mahoor

Traditionally artificial neural networks (ANNs) are trained by minimizing the cross-entropy between a provided groundtruth delta distribution (encoded as one-hot vector) and the ANN's predictive softmax distribution.

Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing

no code implementations • 5 Mar 2019 • Behzad Hasani, Pooran Singh Negi, Mohammad H. Mahoor

This paper introduces Bounded Residual Gradient Networks (BReG-Net) for facial expression recognition, in which the shortcut connection between the input and the output of the ResNet module is replaced with a differentiable function with a bounded gradient.

Facial Expression Recognition Facial Expression Recognition (FER)