Memory based fusion for multi-modal deep learning

TL;DR

This paper introduces a Memory based Attentive Fusion layer for multi-modal deep learning that captures long-term dependencies and improves fusion performance over naive methods.

Contribution

The paper proposes a novel fusion layer incorporating explicit memory and attention mechanisms to better model long-term dependencies in multi-modal data.

Findings

Enhanced performance on multiple datasets

Generalizes across different modalities and networks

Outperforms naive fusion methods

Abstract

The use of multi-modal data for deep machine learning has shown promise when compared to uni-modal approaches with fusion of multi-modal features resulting in improved performance in several applications. However, most state-of-the-art methods use naive fusion which processes feature streams independently, ignoring possible long-term dependencies within the data during fusion. In this paper, we present a novel Memory based Attentive Fusion layer, which fuses modes by incorporating both the current features and longterm dependencies in the data, thus allowing the model to understand the relative importance of modes over time. We introduce an explicit memory block within the fusion layer which stores features containing long-term dependencies of the fused data. The feature inputs from uni-modal encoders are fused through attentive composition and transformation followed by naive fusion of the resultant memory derived features with layer inputs. Following state-of-the-art methods, we have evaluated the performance and the generalizability of the proposed fusion approach on two different datasets with different modalities. In our experiments, we replace the naive fusion layer in benchmark networks with our proposed layer to enable a fair comparison. Experimental results indicate that the MBAF layer can generalise across different modalities and networks to enhance fusion and improve performance.