English

Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation

Computer Vision and Pattern Recognition 2016-12-28 v1 Computation and Language Machine Learning

Abstract

We present novel method for image-text multi-modal representation learning. In our knowledge, this work is the first approach of applying adversarial learning concept to multi-modal learning and not exploiting image-text pair information to learn multi-modal feature. We only use category information in contrast with most previous methods using image-text pair information for multi-modal embedding. In this paper, we show that multi-modal feature can be achieved without image-text pair information and our method makes more similar distribution with image and text in multi-modal feature space than other methods which use image-text pair information. And we show our multi-modal feature has universal semantic information, even though it was trained for category prediction. Our model is end-to-end backpropagation, intuitive and easily extended to other multi-modal learning work.

Keywords

Cite

@article{arxiv.1612.08354,
  title  = {Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation},
  author = {Gwangbeen Park and Woobin Im},
  journal= {arXiv preprint arXiv:1612.08354},
  year   = {2016}
}

Comments

8 pages, 5 figures

R2 v1 2026-06-22T17:34:25.710Z