lucasdu - 博客园

《深度学习》---笔记

摘要：先占个坑，刷几遍之后再来写阅读全文

posted @ 2017-11-30 22:06 lucasdu 阅读(78) 评论(0) 推荐(0)

Faster-RCNN

摘要： Summary 0. History Love between Kaiming&Ross v2, finally together, happy ever after 1. Objective Reduce the region proposal computation time 2. Model 阅读全文

posted @ 2017-11-23 22:44 lucasdu 阅读(96) 评论(0) 推荐(0)

Fast-RCNN

摘要： Summary 0. History The beginning of love between Kaiming and Ross (Ross, you write I write...) 1. Objective Use a single-stage training algorithm that 阅读全文

posted @ 2017-11-23 00:12 lucasdu 阅读(151) 评论(0) 推荐(0)

SPP-net : Spatial Pyramid Pooling in Deep Convolutional Networks

摘要： Summary 0. History Existing deep convolutional neural networks (CNNs) require a fixed-size (224*224) input image. This is often generated by cropping 阅读全文

posted @ 2017-11-22 17:03 lucasdu 阅读(179) 评论(0) 推荐(0)

R-CNN：region based convolutional networks (rich feature)

摘要： Summary 0. History: ILSVRC 2012 workshop central issue : To what extent do the CNN classification results on ImageNet generalize to object detection r 阅读全文

posted @ 2017-11-22 11:05 lucasdu 阅读(173) 评论(0) 推荐(0)

论文列表

摘要：物体检测模型：R-CNNSPP-netFast R-CNNFaster R-CNNR-FCN: Object Detection via Region-based Fully Convolutional NetworksYOLOSSD:Single Shot MultiBox DetectorYOL 阅读全文

posted @ 2017-11-22 09:53 lucasdu 阅读(301) 评论(0) 推荐(0)

论文总结格式

摘要：出发点： 1. 论文目的 2. 所用方法（算法、模型） 3. 方法特点 4. 与同类方法比较优缺点 5. 个人观点阅读全文

posted @ 2017-11-22 09:33 lucasdu 阅读(261) 评论(0) 推荐(0)

小想法

摘要： 1. 将自然语言处理与图像处理结合，将对图片的描述作为弱监督用处：地点定位帮助图像识别，利用景点信息，在已有字典中搜索关联词，帮助提高识别精度阅读全文

posted @ 2017-11-19 10:01 lucasdu 阅读(165) 评论(0) 推荐(0)