Deep Multimodal Learning with Missing Modality: A Survey
It tackles the problem of model robustness in multimodal AI for researchers and practitioners, but it is incremental as it surveys existing work rather than introducing new methods.
This survey reviews deep learning methods for multimodal learning when some data modalities are missing, addressing performance issues caused by sensor limitations or data loss, and provides a comprehensive analysis of current techniques, applications, and datasets.
During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, negatively affecting performance. Multimodal learning techniques designed to handle missing modalities can mitigate this by ensuring model robustness even when some modalities are unavailable. This survey reviews recent progress in Multimodal Learning with Missing Modality (MLMM), focusing on deep learning methods. It provides the first comprehensive survey that covers the motivation and distinctions between MLMM and standard multimodal learning setups, followed by a detailed analysis of current methods, applications, and datasets, concluding with challenges and future directions.