Sorry, you need to enable JavaScript to visit this website.

Kernelized Dense Layers For Facial Expression Recognition

Citation Author(s):
M.Amine Mahmoudi; Aladine Chetouani; Fatma Boufera; Hedi Tabia
Submitted by:
Mohamed Amine M...
Last updated:
2 November 2020 - 4:37pm
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
Mohamed Amine Mahmoudi
Paper Code:
#2488

Abstract 

Abstract: 

Fully connected layer is an essential component of Convolutional Neural Networks (CNNs), which demonstrates its efficiency in computer vision tasks. The CNN process usually starts with convolution and pooling layers that first break down the input images into features, and then analyze them independently. The result of this process feeds into a fully connected neural network structure which drives the final classification decision. In this paper, we propose a Kernelized Dense Layer (KDL) which captures higher order feature interactions instead of conventional linear relations. We apply this method to Facial Expression Recognition (FER) and evaluate its performance on RAF, FER2013 and ExpW datasets. The experimental results demonstrate the benefits of such layer and show that our model achieves competitive results with respect to the state-of-the-art approaches.

up
1 user has voted: Mohamed Amine Mahmoudi

Comments

Fully connected layer is an essential component of Convolutional Neural Networks (CNNs), which demonstrates its efficiency in computer vision tasks. The CNN process usually starts with convolution and pooling layers that first break down the input images into features, and then analyze them independently. The result of this process feeds into a fully connected neural network structure which drives the final classification decision. In this paper, we propose a Kernelized Dense Layer (KDL) which captures higher order feature interactions instead of conventional linear relations. We apply this method to Facial Expression Recognition (FER) and evaluate its performance on RAF, FER2013 and ExpW datasets. The experimental results demonstrate the benefits of such layer and show that our model achieves competitive results with respect to the state-of-the-art approaches.

Dataset Files

Kernelized Dense Layers For Facial Expression Recognition

(56)