{
  "id": 240030,
  "title": "Object Detection Research Papers, A thread....",
  "url": "/competitions/siim-covid19-detection/discussion/240030",
  "author_name": "",
  "post_date": "2021-05-18T11:01:55.557271300Z",
  "votes": 15,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hey everyone !</p>\n<p>I am making this paper thread so that people at each level (from beginners to experts) in the field of Computer Vision can learn about different approaches to solve this problem. Hope other people also contribute to this thread !!</p>\n<p>Happy Kaggling !!</p>\n<ul>\n<li><p>VGG 16 - <a href=\"https://arxiv.org/abs/1409.1556\" target=\"_blank\">https://arxiv.org/abs/1409.1556</a></p></li>\n<li><p>ResNet - <a href=\"https://arxiv.org/abs/1512.03385\" target=\"_blank\">https://arxiv.org/abs/1512.03385</a></p></li>\n<li><p>Inception Model - <a href=\"https://arxiv.org/abs/1409.4842\" target=\"_blank\">https://arxiv.org/abs/1409.4842</a></p></li>\n<li><p>Convoluted Sliding Window - <a href=\"https://arxiv.org/abs/1312.6229\" target=\"_blank\">https://arxiv.org/abs/1312.6229</a></p></li>\n<li><p>YOLO and Anchor Box - <a href=\"https://arxiv.org/abs/1506.02640\" target=\"_blank\">https://arxiv.org/abs/1506.02640</a></p></li>\n<li><p>R-CNN - <a href=\"https://arxiv.org/abs/1311.2524\" target=\"_blank\">https://arxiv.org/abs/1311.2524</a></p></li>\n<li><p>Fast R-CNN - <a href=\"https://arxiv.org/abs/1504.08083\" target=\"_blank\">https://arxiv.org/abs/1504.08083</a></p></li>\n<li><p>Faster R-CNN - <a href=\"https://arxiv.org/abs/1506.01497\" target=\"_blank\">https://arxiv.org/abs/1506.01497</a></p></li>\n<li><p>EfficientDet: Scalable and Efficient Object Detection - <a href=\"https://arxiv.org/abs/1911.09070\" target=\"_blank\">https://arxiv.org/abs/1911.09070</a></p></li>\n<li><p>YOLOv4: Optimal Speed and Accuracy of Object Detection - <a href=\"https://arxiv.org/abs/2004.10934\" target=\"_blank\">https://arxiv.org/abs/2004.10934</a></p></li>\n<li><p>Evolution of YOLO algorithms - <a href=\"https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&amp;isAllowed=y\" target=\"_blank\">https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&amp;isAllowed=y</a></p></li>\n<li><p>Detectron2 - <a href=\"https://github.com/facebookresearch/detectron2\" target=\"_blank\">https://github.com/facebookresearch/detectron2</a></p></li>\n<li><p>Transformer based E-to-E Object Detection - <a href=\"https://arxiv.org/pdf/2005.12872.pdf\" target=\"_blank\">https://arxiv.org/pdf/2005.12872.pdf</a></p></li>\n<li><p>[SOTA] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows - <a href=\"https://arxiv.org/pdf/2103.14030v1.pdf\" target=\"_blank\">https://arxiv.org/pdf/2103.14030v1.pdf</a></p></li>\n<li><p>Small-Object Detection [YOLO, SSD, Faster RCNN] A Survey -<a href=\"https://www.hindawi.com/journals/jece/2020/3189691\" target=\"_blank\">https://www.hindawi.com/journals/jece/2020/3189691</a></p></li>\n<li><p>A Survey of Deep Learning-based Object Detection - <a href=\"https://arxiv.org/abs/1907.09408v2\" target=\"_blank\">https://arxiv.org/abs/1907.09408v2</a></p></li>\n</ul>",
  "messages": [
    {
      "id": "1312979",
      "postDate": "05/18/2021 11:01:55",
      "content": "<p>Hey everyone !</p>\n<p>I am making this paper thread so that people at each level (from beginners to experts) in the field of Computer Vision can learn about different approaches to solve this problem. Hope other people also contribute to this thread !!</p>\n<p>Happy Kaggling !!</p>\n<ul>\n<li><p>VGG 16 - <a href=\"https://arxiv.org/abs/1409.1556\" target=\"_blank\">https://arxiv.org/abs/1409.1556</a></p></li>\n<li><p>ResNet - <a href=\"https://arxiv.org/abs/1512.03385\" target=\"_blank\">https://arxiv.org/abs/1512.03385</a></p></li>\n<li><p>Inception Model - <a href=\"https://arxiv.org/abs/1409.4842\" target=\"_blank\">https://arxiv.org/abs/1409.4842</a></p></li>\n<li><p>Convoluted Sliding Window - <a href=\"https://arxiv.org/abs/1312.6229\" target=\"_blank\">https://arxiv.org/abs/1312.6229</a></p></li>\n<li><p>YOLO and Anchor Box - <a href=\"https://arxiv.org/abs/1506.02640\" target=\"_blank\">https://arxiv.org/abs/1506.02640</a></p></li>\n<li><p>R-CNN - <a href=\"https://arxiv.org/abs/1311.2524\" target=\"_blank\">https://arxiv.org/abs/1311.2524</a></p></li>\n<li><p>Fast R-CNN - <a href=\"https://arxiv.org/abs/1504.08083\" target=\"_blank\">https://arxiv.org/abs/1504.08083</a></p></li>\n<li><p>Faster R-CNN - <a href=\"https://arxiv.org/abs/1506.01497\" target=\"_blank\">https://arxiv.org/abs/1506.01497</a></p></li>\n<li><p>EfficientDet: Scalable and Efficient Object Detection - <a href=\"https://arxiv.org/abs/1911.09070\" target=\"_blank\">https://arxiv.org/abs/1911.09070</a></p></li>\n<li><p>YOLOv4: Optimal Speed and Accuracy of Object Detection - <a href=\"https://arxiv.org/abs/2004.10934\" target=\"_blank\">https://arxiv.org/abs/2004.10934</a></p></li>\n<li><p>Evolution of YOLO algorithms - <a href=\"https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&amp;isAllowed=y\" target=\"_blank\">https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&amp;isAllowed=y</a></p></li>\n<li><p>Detectron2 - <a href=\"https://github.com/facebookresearch/detectron2\" target=\"_blank\">https://github.com/facebookresearch/detectron2</a></p></li>\n<li><p>Transformer based E-to-E Object Detection - <a href=\"https://arxiv.org/pdf/2005.12872.pdf\" target=\"_blank\">https://arxiv.org/pdf/2005.12872.pdf</a></p></li>\n<li><p>[SOTA] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows - <a href=\"https://arxiv.org/pdf/2103.14030v1.pdf\" target=\"_blank\">https://arxiv.org/pdf/2103.14030v1.pdf</a></p></li>\n<li><p>Small-Object Detection [YOLO, SSD, Faster RCNN] A Survey -<a href=\"https://www.hindawi.com/journals/jece/2020/3189691\" target=\"_blank\">https://www.hindawi.com/journals/jece/2020/3189691</a></p></li>\n<li><p>A Survey of Deep Learning-based Object Detection - <a href=\"https://arxiv.org/abs/1907.09408v2\" target=\"_blank\">https://arxiv.org/abs/1907.09408v2</a></p></li>\n</ul>",
      "rawMarkdown": "Hey everyone !\n\nI am making this paper thread so that people at each level (from beginners to experts) in the field of Computer Vision can learn about different approaches to solve this problem. Hope other people also contribute to this thread !!\n\nHappy Kaggling !!\n\n- VGG 16 - https://arxiv.org/abs/1409.1556\n\n- ResNet - https://arxiv.org/abs/1512.03385\n\n- Inception Model - https://arxiv.org/abs/1409.4842\n\n- Convoluted Sliding Window - https://arxiv.org/abs/1312.6229\n\n- YOLO and Anchor Box - https://arxiv.org/abs/1506.02640\n\n- R-CNN - https://arxiv.org/abs/1311.2524\n\n- Fast R-CNN - https://arxiv.org/abs/1504.08083\n\n- Faster R-CNN - https://arxiv.org/abs/1506.01497\n\n- EfficientDet: Scalable and Efficient Object Detection - https://arxiv.org/abs/1911.09070\n\n- YOLOv4: Optimal Speed and Accuracy of Object Detection - https://arxiv.org/abs/2004.10934\n\n- Evolution of YOLO algorithms - https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&isAllowed=y\n\n- Detectron2 - https://github.com/facebookresearch/detectron2\n\n- Transformer based E-to-E Object Detection - https://arxiv.org/pdf/2005.12872.pdf\n\n- [SOTA] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows - https://arxiv.org/pdf/2103.14030v1.pdf\n\n- Small-Object Detection [YOLO, SSD, Faster RCNN] A Survey -https://www.hindawi.com/journals/jece/2020/3189691\n\n- A Survey of Deep Learning-based Object Detection - https://arxiv.org/abs/1907.09408v2",
      "votes": null
    },
    {
      "id": "1314381",
      "postDate": "05/19/2021 06:21:21",
      "content": "<p>😎🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠</p>",
      "rawMarkdown": "😎🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1314381,
      "author_name": "bjky0987",
      "author_url": "",
      "post_date": "05/19/2021 06:21:21",
      "content": "<p>😎🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1312979": "Hey everyone !\n\nI am making this paper thread so that people at each level (from beginners to experts) in the field of Computer Vision can learn about different approaches to solve this problem. Hope other people also contribute to this thread !!\n\nHappy Kaggling !!\n\n- VGG 16 - https://arxiv.org/abs/1409.1556\n\n- ResNet - https://arxiv.org/abs/1512.03385\n\n- Inception Model - https://arxiv.org/abs/1409.4842\n\n- Convoluted Sliding Window - https://arxiv.org/abs/1312.6229\n\n- YOLO and Anchor Box - https://arxiv.org/abs/1506.02640\n\n- R-CNN - https://arxiv.org/abs/1311.2524\n\n- Fast R-CNN - https://arxiv.org/abs/1504.08083\n\n- Faster R-CNN - https://arxiv.org/abs/1506.01497\n\n- EfficientDet: Scalable and Efficient Object Detection - https://arxiv.org/abs/1911.09070\n\n- YOLOv4: Optimal Speed and Accuracy of Object Detection - https://arxiv.org/abs/2004.10934\n\n- Evolution of YOLO algorithms - https://www.theseus.fi/bitstream/handle/10024/452552/Do_Thuan.pdf?sequence=2&isAllowed=y\n\n- Detectron2 - https://github.com/facebookresearch/detectron2\n\n- Transformer based E-to-E Object Detection - https://arxiv.org/pdf/2005.12872.pdf\n\n- [SOTA] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows - https://arxiv.org/pdf/2103.14030v1.pdf\n\n- Small-Object Detection [YOLO, SSD, Faster RCNN] A Survey -https://www.hindawi.com/journals/jece/2020/3189691\n\n- A Survey of Deep Learning-based Object Detection - https://arxiv.org/abs/1907.09408v2",
    "1314381": "😎🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠🤠"
  },
  "source": "meta"
}