Context Matters: Vision-Based Depression Detection Comparing Classical and Deep Approaches

2026-04-11

AI Summary

This study systematically evaluates the accuracy, fairness, and generalization capabilities of classical versus deep learning approaches for cross-context visual depression detection. Leveraging two distinct interaction scenarios—mother–child dyads (TPOT) and clinician–patient interviews (Pitt)—the authors compare handcrafted visual features paired with support vector machines (SVM) against temporal embeddings derived from FMAE-IAT fed into a multilayer perceptron (MLP). The work reveals, for the first time, that depressive behavioral manifestations exhibit strong context specificity: classical methods achieve higher accuracy across both settings and demonstrate significantly better fairness than deep learning models in the clinician–patient context. However, both paradigms show limited cross-context generalization. These findings provide empirical evidence and methodological insights for developing context-sensitive depression recognition systems.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Multimodal Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The classical approach to detecting depression from vision emphasizes interpretable features, such as facial expression, and classifiers such as the Support Vector Machine (SVM). With the advent of deep learning, there has been a shift in feature representations and classification approaches. Contemporary approaches use learnt features from general-purpose vision models such as VGGNet to train machine learning models. Little is known about how classical and deep approaches compare in depression detection with respect to accuracy, fairness, and generalizability, especially across contexts. To address these questions, we compared classical and deep approaches to the detection of depression in the visual modality in two different contexts: Mother-child interactions in the TPOT database and patient-clinician interviews in the Pitt database. In the former, depression was operationalized as a history of depression per the DSM and current or recent clinically significant symptoms. In the latter, all participants met initial criteria for depression per DSM, and depression was reassessed over the course of treatment. The classical approach included handcrafted features with SVM classifiers. Learnt features were turn-level embeddings from the FMAE-IAT that were combined with Multi-Layer Perceptron classifiers. The classical approach achieved higher accuracy in both contexts. It was also significantly fairer than the deep approach in the patient-clinician context. Cross-context generalizability was modest at best for both approaches, which suggests that depression may be context-specific.

Problem

• depression detection
• classical approach
• deep learning
• fairness
• generalizability

Innovation

• depression detection
• classical vs deep learning
• fairness
• cross-context generalizability
• vision-based assessment