Papers › Local Multi-Head Channel Self-Attention for Facial Expression Recognition

Local Multi-Head Channel Self-Attention for Facial Expression Recognition

14 Nov 2021arXiv:2111.07224archive 2025-07-28

Roberto Pecoraro, Valerio Basile, Viviana Bono, Sara Gallo

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.

Paper PDF Code

Code

bodhis4ttva/lhc_net officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Facial Expression Recognition Facial Expression Recognition (FER)

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Facial Expression Recognition (FER)	FER2013	LHC-Net	Accuracy	74.42	#9 of 17	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections