《R-FCN-3000 at 30fps：Decoupling Detection and Classification》论文笔记
1. 概述 导读：这篇文章提出的模型叫做R-FCN-3000（3000类目标）是一个目标定位与目标分类相互独立的实时大规模（分类数多）检测器，其含义是将目标定位与分类解耦，分别预测目标置信度（含检测框）与分类概率，最后将两个结果组合得到检测结果。该算法是在R-FCN的基础上进行修改得到的，但是原始的是COCO的80个类，在分类数目增加的情况下通过聚类的方式缩小头部（聚类分类的类别），从而加速检测。
相关文章
- 1. 论文阅读笔记（三十五）：R-FCN-3000 at 30fps: Decoupling Detection and Classification
- 2. Traffic-Sign Detection and Classification in the Wild 论文笔记
- 3. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 4. R-FCN-3000 at 30fps: Decoupling Detection and Classification
- 5. 《EfficientDet：Scalable and Efficient Object Detection》论文笔记
- 6. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（三）
- 7. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（五）
- 8. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（四）
- 9. 论文笔记-DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
- 10. 论文阅读笔记《RepMet Representative-based metric learning for classification and few-shot object detection》
- 更多相关文章...
- • CAP理论是什么？ - NoSQL教程
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • RxJava操作符（七）Conditional and Boolean
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文阅读笔记（三十五）：R-FCN-3000 at 30fps: Decoupling Detection and Classification
- 2. Traffic-Sign Detection and Classification in the Wild 论文笔记
- 3. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 4. R-FCN-3000 at 30fps: Decoupling Detection and Classification
- 5. 《EfficientDet：Scalable and Efficient Object Detection》论文笔记
- 6. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（三）
- 7. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（五）
- 8. 论文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻译（四）
- 9. 论文笔记-DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification
- 10. 论文阅读笔记《RepMet Representative-based metric learning for classification and few-shot object detection》