CVJul 31, 2022

Analysis of Semi-Supervised Methods for Facial Expression Recognition

arXiv:2208.00544v113 citationsh-index: 7Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses the data annotation bottleneck for researchers and practitioners in facial expression recognition, but it is incremental as it applies existing methods to a new domain.

The paper tackles the problem of reducing reliance on labeled data for facial expression recognition by conducting a comparative study of eight semi-supervised learning methods on three datasets, showing that using as little as 250 labeled samples per class can achieve performance comparable to fully-supervised methods.

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

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes