Progressive Fusion for Multimodal Integration

Integration of multimodal information from various sources has been shown to boost the performance of machine learning models and thus has received increased attention in recent years. Often such models use deep modality-specific networks to obtain unimodal features which are combined to obtain "late-fusion" representations. However, these designs run the risk of information loss in the respective unimodal pipelines. On the other hand, "early-fusion" methodologies, which combine features early, suffer from the problems associated with feature heterogeneity and high sample complexity. In this work, we present an iterative representation refinement approach, called Progressive Fusion, which mitigates the issues with late fusion representations. Our model-agnostic technique introduces backward connections that make late stage fused representations available to early layers, improving the expressiveness of the representations at those stages, while retaining the advantages of late fusion designs. We test Progressive Fusion on tasks including affective sentiment detection, multimedia analysis, and time series fusion with different models, demonstrating its versatility. We show that our approach consistently improves performance, for instance attaining a 5% reduction in MSE and 40% improvement in robustness on multimodal time series prediction.