《CNN Paper》1.0 神经网络经典必读论文12篇

        最近开启了论文100计划,准备阅读整理100篇CV领域经典论文,其中模型中最重要的便是神经网络,为了更好的深入学习CV领域,选择了经典11篇论文进行精度整理,这里相当于一个目录。

目录

一.《LetNet》麻雀虽小,五脏俱全

二.《AlexNet》开山之作,经典必读

三.《VggNet》

四.《GoogleNet》

五.《ResNet》从此打开卷积层爆炸新大门!

六.《DenseNet》

七.《MobileNet》

八.《ShuffleNet》

九.《SENet》

十.《EfficientNet》

十一.《CSPNET》


一.《LetNet》麻雀虽小,五脏俱全

1.博客:

2.论文:404 Not Fount

3.代码:

二.《AlexNet》开山之作,经典必读

1.博客:

2.论文:ImageNet Classification with Deep Convolutional Neural Networks

3.代码:

三.《VggNet》

1.博客:

2.论文:https://arxiv.org/pdf/1409.1556.pdf

3.代码:

四.《GoogleNet》

1.博客:

2.论文:https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf

3.代码:

五.《ResNet》从此打开卷积层爆炸新大门!

1.博客:

2.论文:https://openaccess.thecvf.com/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf

3.代码:

六.《DenseNet》

1.博客:

2.论文:https://arxiv.org/pdf/1608.06993.pdf

3.代码:

七.《MobileNet》

1.博客:

2.论文:https://arxiv.org/pdf/1704.04861.pdf

3.代码:

八.《ShuffleNet》

1.博客:

2.论文:https://arxiv.org/pdf/1707.01083.pdf

3.代码:

九.《SENet》

1.博客:

2.论文:https://arxiv.org/pdf/1709.01507.pdf

3.代码:

十.《EfficientNet》

1.博客:

2.论文:https://arxiv.org/pdf/1905.11946.pdf

3.代码:

十一.《CSPNET》

1.博客:

2.论文:https://arxiv.org/pdf/1911.11929.pdf

3.代码:

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection per- formance tends to degrade with increasing the IoU thresh- olds. Two main factors are responsible for this: 1) over- fitting during training, due to exponentially vanishing pos- itive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the in- put hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these prob- lems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selec- tive against close false positives. The detectors are trained stage by stage, leveraging the observation that the out- put of a detector is a good distribution for training the next higher quality detector. The resampling of progres- sively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reduc- ing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challeng- ing COCO dataset. Experiments also show that the Cas- cade R-CNN is widely applicable across detector architec- tures, achieving consistent gains independently of the base- line detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值