A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter

TL;DR

This paper introduces Wander, a low-rank sequence multimodal adapter that enhances transfer learning by efficiently fusing multiple modalities and modeling their interactions with reduced parameters.

Contribution

Wander is a novel low-rank, tensor-based adapter that enables efficient, token-level multimodal interaction and extends transfer learning to multiple modalities beyond vision-language tasks.

Findings

Wander outperforms existing methods on various multimodal datasets.

It achieves significant parameter reduction while maintaining high performance.

The approach demonstrates universality across different modality combinations.

Abstract

Efficient transfer learning methods such as adapter-based methods have shown great success in unimodal models and vision-language models. However, existing methods have two main challenges in fine-tuning multimodal models. Firstly, they are designed for vision-language tasks and fail to extend to situations where there are more than two modalities. Secondly, they exhibit limited exploitation of interactions between modalities and lack efficiency. To address these issues, in this paper, we propose the loW-rank sequence multimodal adapter (Wander). We first use the outer product to fuse the information from different modalities in an element-wise way effectively. For efficiency, we use CP decomposition to factorize tensors into rank-one components and achieve substantial parameter reduction. Furthermore, we implement a token-level low-rank decomposition to extract more fine-grained features and sequence relationships between modalities. With these designs, Wander enables token-level interactions between sequences of different modalities in a parameter-efficient way. We conduct extensive experiments on datasets with different numbers of modalities, where Wander outperforms state-of-the-art efficient transfer learning methods consistently. The results fully demonstrate the effectiveness, efficiency and universality of Wander.