Analysis of Semi-Supervised Methods for Facial Expression Recognition

TL;DR

This paper evaluates semi-supervised learning methods for facial expression recognition, demonstrating that with minimal labeled data, these methods can achieve performance comparable to fully-supervised models, thus reducing labeling effort.

Contribution

It provides a comprehensive comparison of eight semi-supervised methods on FER datasets, highlighting their effectiveness with limited labeled data and facilitating future research.

Findings

Semi-supervised methods perform well with as few as 250 labeled samples per class.

Semi-supervised approaches can match fully-supervised performance with less labeled data.

The study offers a benchmark for semi-supervised FER methods.

Abstract

Training deep neural networks for image recognition often requires large-scale human annotated data. To reduce the reliance of deep neural solutions on labeled data, state-of-the-art semi-supervised methods have been proposed in the literature. Nonetheless, the use of such semi-supervised methods has been quite rare in the field of facial expression recognition (FER). In this paper, we present a comprehensive study on recently proposed state-of-the-art semi-supervised learning methods in the context of FER. We conduct comparative study on eight semi-supervised learning methods, namely Pi-Model, Pseudo-label, Mean-Teacher, VAT, MixMatch, ReMixMatch, UDA, and FixMatch, on three FER datasets (FER13, RAF-DB, and AffectNet), when various amounts of labeled samples are used. We also compare the performance of these methods against fully-supervised training. Our study shows that when training existing semi-supervised methods on as little as 250 labeled samples per class can yield comparable performances to that of fully-supervised methods trained on the full labeled datasets. To facilitate further research in this area, we make our code publicly available at: https://github.com/ShuvenduRoy/SSL_FER