# FERAtt: Facial Expression Recognition with Attention Net

## TL;DR

This paper introduces FERAtt, an end-to-end facial expression recognition network that employs attention mechanisms and Gaussian-based representation, demonstrating superior performance on synthetic datasets derived from BU3DFE and CK+.

## Contribution

The paper proposes a novel attention-based architecture with a Gaussian structure loss for improved facial expression recognition, validated on synthetic datasets.

## Key findings

- Outperforms baseline models like PreActResNet18
- Effective attention focusing on facial regions
- Robust expression recognition on synthetic datasets

## Abstract

We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based on two fundamental complementary components: (1) facial image correction and attention and (2) facial expression representation and classification. The first component uses an encoder-decoder style network and a convolutional feature extractor that are pixel-wise multiplied to obtain a feature attention map. The second component is responsible for obtaining an embedded representation and classification of the facial expression. We propose a loss function that creates a Gaussian structure on the representation space. To demonstrate the proposed method, we create two larger and more comprehensive synthetic datasets using the traditional BU3DFE and CK+ facial datasets. We compared results with the PreActResNet18 baseline. Our experiments on these datasets have shown the superiority of our approach in recognizing facial expressions.