Deep Metric Structured Learning For Facial Expression Recognition

Abstract

We propose a deep metric learning model to create embedded sub-spaces with a well defined structure. A new loss function that imposes Gaussian structures on the output space is introduced to create these sub-spaces thus shaping the distribution of the data. Having a mixture of Gaussians solution space is advantageous given its simplified and well established structure. It allows fast discovering of classes within classes and the identification of mean representatives at the centroids of individual classes. We also propose a new semi-supervised method to create sub-classes. We illustrate our methods on the facial expression recognition problem and validate results on the FER+, AffectNet, Extended Cohn-Kanade (CK+), BU-3DFE, and JAFFE datasets. We experimentally demonstrate that the learned embedding can be successfully used for various applications including expression retrieval and emotion recognition.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfernandez2020deep

Related papers

• Deep Metric Learning Via Facility Location (2016)17.16
• GSSF: Generalized Structural Sparse Function For Deep Cross-modal Metric Learning (2024)7.74
• A Compact Embedding For Facial Expression Similarity (2018)14.39
• Towards Interpretable Deep Metric Learning With Structural Matching (2021)15.87
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Attention-based Ensemble For Deep Metric Learning (2018)15.90
• Visual Explanation For Deep Metric Learning (2019)14.36