AkihikoWatanabe / paper_notes

たまに追加される論文メモ
https://AkihikoWatanabe.github.io/paper_notes
17 stars 0 forks source link

Learning Multimodal Data Augmentation in Feature Space, ICLR'23 #546

Open AkihikoWatanabe opened 1 year ago

AkihikoWatanabe commented 1 year ago

https://arxiv.org/abs/2212.14453

AkihikoWatanabe commented 1 year ago

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.

Translation (by gpt-3.5-turbo)

AkihikoWatanabe commented 11 months ago

Data Augmentationは基本的に単体のモダリティに閉じて行われるが、 マルチモーダルな設定において、モダリティ同士がどう関係しているか、どの変換を利用すべきかわからない時に、どのようにデータ全体のsemantic structureを維持しながら、Data Augmentationできるか?という話らしい