Biased Heritage: How Datasets Shape Models in Facial Expression Recognition

arXiv:2503.03446 · cs.CV, cs.CY · Submitted 2025-03-05 · Read on arXiv

cs.CV, cs.CY

Submitted: 2025-03-05

Updated: 2025-03-05

Code: https://github.com/arin-upna/biased-heritage

Terminology

• Accuracy — 14× in this paper · explained in 1 episode
• Facial Expression Recognition — 13× in this paper
• Adaptation — 9× in this paper · explained in 1 episode
• Combined Error Variance — 4× in this paper
• Selection Bias — 4× in this paper · explained in 4 episodes
• Artificial Intelligence (AI) — 3× in this paper · explained in 2 episodes
• Overall Disparity — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Symmetric Distance Error — 3× in this paper
• Homogeneity — 2× in this paper · explained in 2 episodes
• True Positive Rate — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Affective Computing — 1× in this paper · explained in 1 episode
• Algorithmic Bias — 1× in this paper · explained in 1 episode
• Causal Reasoning — 1× in this paper · explained in 2 episodes
• Effective Number of Species — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• False Detection Rate — 1× in this paper
• False Negative Rate — 1× in this paper
• False Positive Rate — 1× in this paper
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Onderzoeksprogramma Artificiele Intelligentie — 1× in this paper
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Shannon Evenness Index — 1× in this paper
• Systematic Bias — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Blackbox Post-Processing for Multiclass Fairness
• The Measure and Mismeasure of Fairness
• The impossibility of "fairness": a generalized impossibility result for decisions
• Responsible AI: Gender bias assessment in emotion recognition
• Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups
• Max-Margin Object Detection
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models