Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Freire-Obregón, David, Salas-Cáceres, José, Lorenzo-Navarro, Javier, Santana, Oliverio J., Hernández-Sosa, Daniel, Castrillón-Santana, Modesto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915556080222208
author Freire-Obregón, David
Salas-Cáceres, José
Lorenzo-Navarro, Javier
Santana, Oliverio J.
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
author_facet Freire-Obregón, David
Salas-Cáceres, José
Lorenzo-Navarro, Javier
Santana, Oliverio J.
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
contents Facial expression recognition (FER) must remain robust under both cultural variation and perceptually degraded visual conditions, yet most existing evaluations assume homogeneous data and high-quality imagery. We introduce an agent-based, streaming benchmark that reveals how cross-cultural composition and progressive blurring interact to shape face recognition robustness. Each agent operates in a frozen CLIP feature space with a lightweight residual adapter trained online at sigma=0 and fixed during testing. Agents move and interact on a 5x5 lattice, while the environment provides inputs with sigma-scheduled Gaussian blur. We examine monocultural populations (Western-only, Asian-only) and mixed environments with balanced (5/5) and imbalanced (8/2, 2/8) compositions, as well as different spatial contact structures. Results show clear asymmetric degradation curves between cultural groups: JAFFE (Asian) populations maintain higher performance at low blur but exhibit sharper drops at intermediate stages, whereas KDEF (Western) populations degrade more uniformly. Mixed populations exhibit intermediate patterns, with balanced mixtures mitigating early degradation, but imbalanced settings amplify majority-group weaknesses under high blur. These findings quantify how cultural composition and interaction structure influence the robustness of FER as perceptual conditions deteriorate.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13557
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents
Freire-Obregón, David
Salas-Cáceres, José
Lorenzo-Navarro, Javier
Santana, Oliverio J.
Hernández-Sosa, Daniel
Castrillón-Santana, Modesto
Computer Vision and Pattern Recognition
Artificial Intelligence
Facial expression recognition (FER) must remain robust under both cultural variation and perceptually degraded visual conditions, yet most existing evaluations assume homogeneous data and high-quality imagery. We introduce an agent-based, streaming benchmark that reveals how cross-cultural composition and progressive blurring interact to shape face recognition robustness. Each agent operates in a frozen CLIP feature space with a lightweight residual adapter trained online at sigma=0 and fixed during testing. Agents move and interact on a 5x5 lattice, while the environment provides inputs with sigma-scheduled Gaussian blur. We examine monocultural populations (Western-only, Asian-only) and mixed environments with balanced (5/5) and imbalanced (8/2, 2/8) compositions, as well as different spatial contact structures. Results show clear asymmetric degradation curves between cultural groups: JAFFE (Asian) populations maintain higher performance at low blur but exhibit sharper drops at intermediate stages, whereas KDEF (Western) populations degrade more uniformly. Mixed populations exhibit intermediate patterns, with balanced mixtures mitigating early degradation, but imbalanced settings amplify majority-group weaknesses under high blur. These findings quantify how cultural composition and interaction structure influence the robustness of FER as perceptual conditions deteriorate.
title Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.13557