ShaLa: Multimodal Shared Latent Space Modelling
This work addresses the challenge of capturing high-level semantic concepts shared across modalities for tasks like joint multimodal synthesis and cross-modal inference, representing an incremental improvement over existing multimodal VAEs.
The paper tackles the problem of learning shared latent representations across multimodal data, where existing multimodal VAEs struggle with expressive joint variational posteriors and low-quality synthesis. The proposed ShaLa framework integrates a novel architectural inference model and a diffusion prior, achieving superior coherence and synthesis quality compared to state-of-the-art multimodal VAEs across multiple benchmarks.
This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across inputs, which can inadvertently obscure the high-level semantic concepts that are shared across modalities. Notably, Multimodal VAEs with low-dimensional latent variables are designed to capture shared representations, enabling various tasks such as joint multimodal synthesis and cross-modal inference. However, multimodal VAEs often struggle to design expressive joint variational posteriors and suffer from low-quality synthesis. In this work, ShaLa addresses these challenges by integrating a novel architectural inference model and a second-stage expressive diffusion prior, which not only facilitates effective inference of shared latent representation but also significantly improves the quality of downstream multimodal synthesis. We validate ShaLa extensively across multiple benchmarks, demonstrating superior coherence and synthesis quality compared to state-of-the-art multimodal VAEs. Furthermore, ShaLa scales to many more modalities while prior multimodal VAEs have fallen short in capturing the increasing complexity of the shared latent space.