{
  "id": "2001.06658",
  "version": "v1",
  "published": "2020-01-18T12:19:19.000Z",
  "updated": "2020-01-18T12:19:19.000Z",
  "title": "Text-to-Image Generation with Attention Based Recurrent Neural Networks",
  "authors": [
    "Tehseen Zia",
    "Shahan Arif",
    "Shakeeb Murtaza",
    "Mirza Ahsan Ullah"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using variational auto-encoders and rely on the intractable inference that can hamper their performance, the latter is unstable to train due to Nash equilibrium based objective function. We develop a tractable and stable caption-based image generation model. The model uses an attention-based encoder to learn word-to-pixel dependencies. A conditional autoregressive based decoder is used for learning pixel-to-pixel dependencies and generating images. Experimentations are performed on Microsoft COCO, and MNIST-with-captions datasets and performance is evaluated by using the Structural Similarity Index. Results show that the proposed model performs better than contemporary approaches and generate better quality images. Keywords: Generative image modeling, autoregressive image modeling, caption-based image generation, neural attention, recurrent neural networks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-01-18T12:19:19.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "recurrent neural networks",
      "text-to-image generation",
      "generate better quality images",
      "image modeling",
      "stable caption-based image generation model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}