A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection 笔记
2017-07-25 09:13
501 查看
这篇paper主要是针对训练数据时,遮蔽和形变物体的数据集不一定很全面提出的,于是,想到可以用生成网络生成这种数据来进行训练。但是这种数据生成又是很困难的,作者就想到跳过生成数据,直接在Feature Map上做类似的生成。
和生成模型很类似,在Feature Map上引入Adversary去和Detector做对抗训练,训练出最终的模型。
详细的内容可参见paper:
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
找到一篇caffe的github实现:
https://github.com/xiaolonw/adversarial-frcnn
和生成模型很类似,在Feature Map上引入Adversary去和Detector做对抗训练,训练出最终的模型。
详细的内容可参见paper:
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
找到一篇caffe的github实现:
https://github.com/xiaolonw/adversarial-frcnn
相关文章推荐
- [论文笔记]A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- [深度学习论文笔记][CVPR 17 oral]A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- 目标检测“A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection”
- A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- A-Fast-RCNN: Hard positive generation via adversary for object detection
- 对抗学习用于目标检测--A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- 阅读小结:A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- A-Fast-RCNN:Hard Positive Generation via Adversary for Object Detection
- 对抗学习用于目标检测--A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- 对抗学习用于目标检测--A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- 行人检测论文笔记:Fast Feature Pyramids for Object Detection?
- RCNN系列学习笔记(1):Rich feature hierarchies for accurate object detection and semantic segmentation
- 论文笔记 MSCNN:A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- RCNN系列笔记整理(1):Rich feature hierarchies for accurate object detection and semantic segment
- 行人检测论文笔记:Fast Feature Pyramids for Object Detection?
- 多尺度R-CNN论文笔记(5): A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
- rcnn学习笔记:Rich feature hierarchies for accurate object detection and semantic segmentation
- 论文笔记 《Deep Neural Networks for Object Detection》
- 《Focal Loss for Object Detection》阅读笔记
- [论文笔记]Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness