{ "id": 198159, "title": "Papers on Crop Image Detection", "url": "/competitions/cassava-leaf-disease-classification/discussion/198159", "author_name": "", "post_date": "2020-11-20T02:06:28.820305100Z", "votes": 4, "comment_count": 1, "views": 0, "content": "

Hey everyone!

\n

I wanted to start a paper thread and build on it. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!

\n

Research Papers:

\n", "messages": [ { "id": "1084390", "postDate": "11/20/2020 02:06:28", "content": "

Hey everyone!

\n

I wanted to start a paper thread and build on it. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!

\n

Research Papers:

\n", "rawMarkdown": "Hey everyone!\n\nI wanted to start a paper thread and build on it. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\nResearch Papers:\n* [UP-DETR: Unsupervised Pre-training for Object Detection with Transformers](https://arxiv.org/abs/2011.09094) - The model is pre-trained to detect these query patches from the original image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade-off multi-task learning of classification and localization in the pretext task, we freeze the CNN backbone and propose a patch feature reconstruction branch which is jointly optimized with patch detection. (2) To perform multi-query localization, we introduce UP-DETR from single-query patch and extend it to multi-query patches with object query shuffle and attention mask.\n\n* [Strawberry Detection Using a Heterogeneous Multi-Processor Platform](https://arxiv.org/abs/2011.03651) - This paper proposes using the You Only Look Once version 3 (YOLOv3) Convolutional Neural Network (CNN) in combination with utilising image processing techniques for the application of precision farming robots targeting strawberry detection, accelerated on a heterogeneous multiprocessor platform. \n\n* [Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search](https://arxiv.org/abs/2010.15821) - We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training.\n\n* [Bag of Freebies for Training Object Detection Neural Networks](https://arxiv.org/abs/1902.04103)\n\n* [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://arxiv.org/pdf/1906.07155.pdf)\n\n* [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://arxiv.org/pdf/2004.10934v1.pdf)\n\n* [Cascade R-CNN: Delving into High Quality Object Detection](https://arxiv.org/abs/1712.00726)\n\n* [EfficientDet: Scalable and Efficient Object Detection](https://paperswithcode.com/paper/efficientdet-scalable-and-efficient-object)\n\n* [Cascade Mask R-CNN)CBNet: A Novel Composite Backbone Network Architecture for Object Detection](https://paperswithcode.com/paper/cbnet-a-novel-composite-backbone-network)", "votes": null }, { "id": "1084642", "postDate": "11/20/2020 08:27:05", "content": "

Noob question:
\nIn a classification problem, how are you planning to use object detection models?

", "rawMarkdown": "Noob question:\nIn a classification problem, how are you planning to use object detection models?", "votes": null } ], "comments": [ { "id": 1084642, "author_name": "jabertuhin", "author_url": "", "post_date": "11/20/2020 08:27:05", "content": "

Noob question:
\nIn a classification problem, how are you planning to use object detection models?

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1084390": "Hey everyone!\n\nI wanted to start a paper thread and build on it. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\nResearch Papers:\n* [UP-DETR: Unsupervised Pre-training for Object Detection with Transformers](https://arxiv.org/abs/2011.09094) - The model is pre-trained to detect these query patches from the original image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade-off multi-task learning of classification and localization in the pretext task, we freeze the CNN backbone and propose a patch feature reconstruction branch which is jointly optimized with patch detection. (2) To perform multi-query localization, we introduce UP-DETR from single-query patch and extend it to multi-query patches with object query shuffle and attention mask.\n\n* [Strawberry Detection Using a Heterogeneous Multi-Processor Platform](https://arxiv.org/abs/2011.03651) - This paper proposes using the You Only Look Once version 3 (YOLOv3) Convolutional Neural Network (CNN) in combination with utilising image processing techniques for the application of precision farming robots targeting strawberry detection, accelerated on a heterogeneous multiprocessor platform. \n\n* [Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search](https://arxiv.org/abs/2010.15821) - We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training.\n\n* [Bag of Freebies for Training Object Detection Neural Networks](https://arxiv.org/abs/1902.04103)\n\n* [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://arxiv.org/pdf/1906.07155.pdf)\n\n* [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://arxiv.org/pdf/2004.10934v1.pdf)\n\n* [Cascade R-CNN: Delving into High Quality Object Detection](https://arxiv.org/abs/1712.00726)\n\n* [EfficientDet: Scalable and Efficient Object Detection](https://paperswithcode.com/paper/efficientdet-scalable-and-efficient-object)\n\n* [Cascade Mask R-CNN)CBNet: A Novel Composite Backbone Network Architecture for Object Detection](https://paperswithcode.com/paper/cbnet-a-novel-composite-backbone-network)", "1084642": "Noob question:\nIn a classification problem, how are you planning to use object detection models?" }, "source": "meta" }