Generalized Multimodal ELBO

by   Thomas M. Sutter, et al.

Multiple data types naturally co-occur when describing real-world phenomena and learning from them is a long-standing goal in machine learning research. However, existing self-supervised generative models approximating an ELBO are not able to fulfill all desired requirements of multimodal models: their posterior approximation functions lead to a trade-off between the semantic coherence and the ability to learn the joint data distribution. We propose a new, generalized ELBO formulation for multimodal data that overcomes these limitations. The new objective encompasses two previous methods as special cases and combines their benefits without compromises. In extensive experiments, we demonstrate the advantage of the proposed method compared to state-of-the-art models in self-supervised, generative learning tasks.


page 7

page 9

page 18

page 19

page 20

page 23


Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence

Learning from different data types is a long-standing goal in machine le...

Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning

One of the key factors of enabling machine learning models to comprehend...

On the Limitations of Multimodal VAEs

Multimodal variational autoencoders (VAEs) have shown promise as efficie...

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Recently, Self-Supervised Representation Learning (SSRL) has attracted m...

Learning more expressive joint distributions in multimodal variational methods

Data often are formed of multiple modalities, which jointly describe the...

Self-Supervised Deep Visual Odometry with Online Adaptation

Self-supervised VO methods have shown great success in jointly estimatin...