Towards Interpretability in Audio and Visual Affective Machine Learning: A Review
arXiv:2306.08933 · doi:10.1109/TAFFC.2024.3505269
Abstract
Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning.
arXiv comment8 pages, 2 tables
References in corpus (10)
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Deep Facial Expression Recognition: A Survey
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanations
- Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
- From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
- GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
- Towards Relatable Explainable AI with the Perceptual Process
- Graph Capsule Aggregation for Unaligned Multimodal Sequences
- Global Aggregations of Local Explanations for Black Box models