{
  "id": 523898,
  "title": "Further reading and research areas",
  "url": "/competitions/gan-getting-started/discussion/523898",
  "author_name": "sethpointaverage",
  "post_date": "2024-08-03T12:43:32.029000",
  "votes": 6,
  "comment_count": 0,
  "views": 0,
  "content": "<p>While this competition is focused largely on GANs, I wanted to add in a few resources (and interesting research areas) that may be helpful to people wanting to explore different modelling techniques (a couple include VAEs)</p>\n<p>This is a work in progress and I will be updating more resources to this</p>\n<p><strong>Image inpainting:</strong><br>\n<a href=\"https://arxiv.org/abs/2103.10022\" target=\"_blank\">https://arxiv.org/abs/2103.10022</a><br>\n<a href=\"https://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html\" target=\"_blank\">https://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html</a></p>\n<p><strong>Class conditional resources:</strong><br>\nOriginal cGAN paper for reference: <a href=\"https://arxiv.org/abs/1411.1784\" target=\"_blank\">https://arxiv.org/abs/1411.1784</a><br>\nEasy cGAN plugin code - <a href=\"https://github.com/Lornatang/CGAN-PyTorch\" target=\"_blank\">https://github.com/Lornatang/CGAN-PyTorch</a><br>\nTraining GANs with low data: <a href=\"https://arxiv.org/abs/2201.06578\" target=\"_blank\">https://arxiv.org/abs/2201.06578</a> - code at <a href=\"https://github.com/mshahbazi72/transitional-cGAN\" target=\"_blank\">https://github.com/mshahbazi72/transitional-cGAN</a></p>\n<p><strong>Conditional VAE tutorial:</strong><br>\n<a href=\"https://ijdykeman.github.io/ml/2016/12/21/cvae.html\" target=\"_blank\">https://ijdykeman.github.io/ml/2016/12/21/cvae.html</a></p>\n<p><strong>Attentional GANs:</strong><br>\n<a href=\"https://paperswithcode.com/method/sagan\" target=\"_blank\">https://paperswithcode.com/method/sagan</a></p>",
  "messages": [
    {
      "id": 2945457,
      "postDate": "2024-08-03T12:43:32.030Z",
      "content": "<p>While this competition is focused largely on GANs, I wanted to add in a few resources (and interesting research areas) that may be helpful to people wanting to explore different modelling techniques (a couple include VAEs)</p>\n<p>This is a work in progress and I will be updating more resources to this</p>\n<p><strong>Image inpainting:</strong><br>\n<a href=\"https://arxiv.org/abs/2103.10022\" target=\"_blank\">https://arxiv.org/abs/2103.10022</a><br>\n<a href=\"https://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html\" target=\"_blank\">https://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html</a></p>\n<p><strong>Class conditional resources:</strong><br>\nOriginal cGAN paper for reference: <a href=\"https://arxiv.org/abs/1411.1784\" target=\"_blank\">https://arxiv.org/abs/1411.1784</a><br>\nEasy cGAN plugin code - <a href=\"https://github.com/Lornatang/CGAN-PyTorch\" target=\"_blank\">https://github.com/Lornatang/CGAN-PyTorch</a><br>\nTraining GANs with low data: <a href=\"https://arxiv.org/abs/2201.06578\" target=\"_blank\">https://arxiv.org/abs/2201.06578</a> - code at <a href=\"https://github.com/mshahbazi72/transitional-cGAN\" target=\"_blank\">https://github.com/mshahbazi72/transitional-cGAN</a></p>\n<p><strong>Conditional VAE tutorial:</strong><br>\n<a href=\"https://ijdykeman.github.io/ml/2016/12/21/cvae.html\" target=\"_blank\">https://ijdykeman.github.io/ml/2016/12/21/cvae.html</a></p>\n<p><strong>Attentional GANs:</strong><br>\n<a href=\"https://paperswithcode.com/method/sagan\" target=\"_blank\">https://paperswithcode.com/method/sagan</a></p>",
      "rawMarkdown": "While this competition is focused largely on GANs, I wanted to add in a few resources (and interesting research areas) that may be helpful to people wanting to explore different modelling techniques (a couple include VAEs)\n\nThis is a work in progress and I will be updating more resources to this\n\n**Image inpainting:**\nhttps://arxiv.org/abs/2103.10022\nhttps://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html\n\n**Class conditional resources:**\nOriginal cGAN paper for reference: https://arxiv.org/abs/1411.1784\nEasy cGAN plugin code - https://github.com/Lornatang/CGAN-PyTorch\nTraining GANs with low data: https://arxiv.org/abs/2201.06578 - code at https://github.com/mshahbazi72/transitional-cGAN\n\n**Conditional VAE tutorial:**\nhttps://ijdykeman.github.io/ml/2016/12/21/cvae.html\n\n**Attentional GANs:**\nhttps://paperswithcode.com/method/sagan",
      "votes": 6
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2945457": "While this competition is focused largely on GANs, I wanted to add in a few resources (and interesting research areas) that may be helpful to people wanting to explore different modelling techniques (a couple include VAEs)\n\nThis is a work in progress and I will be updating more resources to this\n\n**Image inpainting:**\nhttps://arxiv.org/abs/2103.10022\nhttps://openaccess.thecvf.com/content/ICCV2021/html/Suin_Distillation-Guided_Image_Inpainting_ICCV_2021_paper.html\n\n**Class conditional resources:**\nOriginal cGAN paper for reference: https://arxiv.org/abs/1411.1784\nEasy cGAN plugin code - https://github.com/Lornatang/CGAN-PyTorch\nTraining GANs with low data: https://arxiv.org/abs/2201.06578 - code at https://github.com/mshahbazi72/transitional-cGAN\n\n**Conditional VAE tutorial:**\nhttps://ijdykeman.github.io/ml/2016/12/21/cvae.html\n\n**Attentional GANs:**\nhttps://paperswithcode.com/method/sagan"
  }
}