Shi, Y; Paige, B; Torr, PHS; Siddharth, N; (2021) Relating by Contrasting: A Data-Efficient Framework for Multimodal DGMs. In: Proceedings of the 9th International Conference on Learning Representations (ICLR 2021). (pp. pp. 1-25). ICLR

Preview

Text 1601_relating_by_contrasting_a_data.pdf - Published Version Download (6MB) | Preview

Abstract

Multimodal learning for generative models often refers to the learning of abstract concepts from the commonality of information in multiple modalities, such as vision and language. While it has proven effective for learning generalisable representations, the training of such models often requires a large amount of “related” multimodal data that shares commonality, which can be expensive to come by. To mitigate this, we develop a novel contrastive framework for generative model learning, allowing us to train the model not just by the commonality between modalities, but by the distinction between “related” and “unrelated” multimodal data. We show in experiments that our method enables data-efficient multimodal learning on challenging datasets for various multimodal variational autoencoder (VAE) models. We also show that under our proposed framework, the generative model can accurately identify related samples from unrelated ones, making it possible to make use of the plentiful unlabeled, unpaired multimodal data.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item