Local Multi-Head Channel Self-Attention for Facial Expression Recognition
This work addresses facial expression recognition for computer vision applications, presenting an incremental improvement in efficiency and performance.
The authors tackled facial expression recognition by proposing LHC-Net, a novel self-attention module integrated into convolutional neural networks, achieving a new state-of-the-art on the FER2013 dataset with significantly lower computational cost.
Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily integrated in virtually every convolutional neural network and that is specifically designed for computer vision, the LHC: Local (multi) Head Channel (self-attention). LHC is based on two main ideas: first, we think that in computer vision the best way to leverage the self-attention paradigm is the channel-wise application instead of the more explored spatial attention and that convolution will not be replaced by attention modules like recurrent networks were in NLP; second, a local approach has the potential to better overcome the limitations of convolution than global attention. With LHC-Net we managed to achieve a new state of the art in the famous FER2013 dataset with a significantly lower complexity and impact on the "host" architecture in terms of computational cost when compared with the previous SOTA.