Learning Multimodal Data Augmentation in Feature Space
Preprint
Abstract
The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, such as translation. Moreover, it is challenging to specify reasonable transformations that are not tailored to a particular modality. In this paper, we introduce LeMDA, Learning Multimodal Data Augmentation, an easy-to-use method that automatically learns to jointly augment multimodal data in feature space, with no constraints on the identities of the modalities or the relationship between modalities. We show that LeMDA can (1) profoundly improve the performance of multimodal deep learning architectures, (2) apply to combinations of modalities that have not been previously considered, and (3) achieve state-of-the-art results on a wide range of applications comprised of image, text, and tabular data.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- TeachAugment: Data Augmentation Optimization Using Teacher Knowledge2022
- TCGM: An Information-Theoretic Framework for Semi-supervised Multi-modality Learning2020
- Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering2020
- OnlineAugment: Online Data Augmentation with Less Domain Knowledge2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- EmbraceNet: A robust deep learning architecture for multimodal classificationInformation Fusion, 2019
- MFAS: Multimodal Fusion Architecture Search2019
- Data Augmentation via Latent Space Interpolation for Image Classification2018
- Learning Robust Visual-Semantic Embeddings2017
- Adaptive data augmentation for image classification2016