常见的神经网络模型 AlexNet,VGGNet,GoogleNet,resNet,inceptionV3,Inception-v4,xception等论文下载链接

曾经终败给现在 2022-05-24 07:06 232阅读 0赞

LeNet 1986  
AlexNet 2012 [http://pan.baidu.com/s/1NpEG2，作者:Alex][http_pan.baidu.com_s_1NpEG2_Alex] Krizhevsky,Ilya Sutskever,Geoffrey E.Hinton

VGGNet 2014 [https://arxiv.org/pdf/1409.1556.pdf][https_arxiv.org_pdf_1409.1556.pdf] 6.8% test error,作者:Karen Simonyan,Andrew Zisserman

GoogleNet(inception v1) 2014 [http://arxiv.org/pdf/1409.4842v1.pdf][http_arxiv.org_pdf_1409.4842v1.pdf] Going Deeper with Convolutions, 6.67% test error  
作者:Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich

resNet 2015 [https://arxiv.org/pdf/1512.03385.pdf][https_arxiv.org_pdf_1512.03385.pdf] 3.6% test error,作者:Kaiming He, Xiangyu Zhang,Shaoqing Ren,Jian Sun

inception V2-V3 2015 [http://arxiv.org/abs/1512.00567][http_arxiv.org_abs_1512.00567] 3.6% test error  
作者:Christian Szegedy,Vincent Vanhoucke,Sergey Ioffe,Jonathon Shlens

BN layer [https://arxiv.org/pdf/1502.03167.pdf][https_arxiv.org_pdf_1502.03167.pdf] 4.8% test error,作者:bn Sergey Ioffe,Christian Szegedy

Inception-v4, Inception-ResNet 2016 [http://arxiv.org/abs/1602.07261][http_arxiv.org_abs_1602.07261] 3.08% test error  
作者:Christian Szegedy，Sergey Ioffe，Vincent Vanhoucke

xception 2017 [https://arxiv.org/pdf/1610.02357.pdf][https_arxiv.org_pdf_1610.02357.pdf] 94.5% acc,作者:Francois Chollet

denseNet 2017(best) [https://arxiv.org/abs/1608.06993][https_arxiv.org_abs_1608.06993] 5.29% test error  
MobileNet 2017 [https://arxiv.org/pdf/1704.04861.pdf][https_arxiv.org_pdf_1704.04861.pdf] top1 70.6%  
NasNet 2018 [https://arxiv.org/abs/1707.07012][https_arxiv.org_abs_1707.07012] top1 82.7% top 5 96.2  
SqueezeNet 2016 [http://arxiv.org/abs/1602.07360][http_arxiv.org_abs_1602.07360] top1 60.4% top5 82.5%  
FCN 2016 [https://arxiv.org/abs/1605.06211][https_arxiv.org_abs_1605.06211] 解决end-to-end image semantic segmentation  
DCN 2017 [https://arxiv.org/abs/1703.06211][https_arxiv.org_abs_1703.06211] 可变形卷积

Object Detection  
RCNN 2013 [http://arxiv.org/abs/1311.2524][http_arxiv.org_abs_1311.2524]  
SPPNet 2014 [https://arxiv.org/abs/1406.4729v2][https_arxiv.org_abs_1406.4729v2]  
fast RCNN 2015 [https://arxiv.org/abs/1504.08083][https_arxiv.org_abs_1504.08083]  
faster RCNN 2015 [https://arxiv.org/abs/1506.01497][https_arxiv.org_abs_1506.01497]  
YOLO 2015 [https://arxiv.org/abs/1506.02640][https_arxiv.org_abs_1506.02640]  
SSD 2015 [https://arxiv.org/abs/1512.02325][https_arxiv.org_abs_1512.02325]  
YOLO9000 2016 [https://arxiv.org/abs/1612.08242][https_arxiv.org_abs_1612.08242]  
R-FCN 2016 [https://arxiv.org/abs/1605.06409][https_arxiv.org_abs_1605.06409]  
Deformable-ConvNets 2017 [https://arxiv.org/abs/1703.06211][https_arxiv.org_abs_1703.06211]  
Mask R-CNN 2017 [https://arxiv.org/abs/1703.06870][https_arxiv.org_abs_1703.06870]  
FPN(Feature Pyramid Networks for Object Detection) 2017 [https://arxiv.org/abs/1612.03144][https_arxiv.org_abs_1612.03144] 对不同卷积层进行融合merge

GAN对抗生成网络  
GAN 2014 [https://arxiv.org/abs/1406.2661][https_arxiv.org_abs_1406.2661]  
DCGAN 2015 [http://arxiv.org/abs/1511.06434][http_arxiv.org_abs_1511.06434]  
LSGAN 2016 [https://arxiv.org/abs/1611.04076][https_arxiv.org_abs_1611.04076]  
WGAN 2017 [https://arxiv.org/abs/1701.07875][https_arxiv.org_abs_1701.07875]  
WGAN-GP [https://arxiv.org/abs/1704.00028][https_arxiv.org_abs_1704.00028] improved wgan  
BEGAN [https://arxiv.org/abs/1703.10717][https_arxiv.org_abs_1703.10717]

词向量  
word2vec，固定的词向量，词与词的距离关系  
2013，Efficient Estimation of Word Representations in Vector Space，[https://arxiv.org/abs/1301.3781][https_arxiv.org_abs_1301.3781] ，ICLR  
2013，Distributed Representations of Words and Phrases and their Compositionality. [https://arxiv.org/abs/1310.4546，NIPS][https_arxiv.org_abs_1310.4546_NIPS]

ELMo，动态的词向量，相同的词在不同的语境词向量不同  
2018，Deep contextualized word representations [https://arxiv.org/abs/1802.05365][https_arxiv.org_abs_1802.05365]

BERT，从词向量变成了词向量+句向量+位置向量  
2018 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [https://arxiv.org/abs/1810.04805][https_arxiv.org_abs_1810.04805]

attention  
2014 Recurrent Models of Visual Attention [https://arxiv.org/abs/1406.6247][https_arxiv.org_abs_1406.6247] 从图片的识别方式开始引出attention，但不是真正的attention  
2014 Neural Machine Translation by Jointly Learning to Align and Translate [https://arxiv.org/abs/1409.0473][https_arxiv.org_abs_1409.0473] 在NLP中第一个使用attention机制,Tensorflow中有BahdanauAttention  
2015 Effective Approaches to Attention-based Neural Machine Translation [https://arxiv.org/abs/1508.04025][https_arxiv.org_abs_1508.04025] Tensorflow中有LuongAttention  
2017 Attention Is All You Need [https://arxiv.org/abs/1706.03762][https_arxiv.org_abs_1706.03762] transformer中的self\_attention，encode\_decode\_attention

[http_pan.baidu.com_s_1NpEG2_Alex]: http://pan.baidu.com/s/1NpEG2%EF%BC%8C%E4%BD%9C%E8%80%85:Alex
[https_arxiv.org_pdf_1409.1556.pdf]: https://arxiv.org/pdf/1409.1556.pdf
[http_arxiv.org_pdf_1409.4842v1.pdf]: http://arxiv.org/pdf/1409.4842v1.pdf
[https_arxiv.org_pdf_1512.03385.pdf]: https://arxiv.org/pdf/1512.03385.pdf
[http_arxiv.org_abs_1512.00567]: http://arxiv.org/abs/1512.00567
[https_arxiv.org_pdf_1502.03167.pdf]: https://arxiv.org/pdf/1502.03167.pdf
[http_arxiv.org_abs_1602.07261]: http://arxiv.org/abs/1602.07261
[https_arxiv.org_pdf_1610.02357.pdf]: https://arxiv.org/pdf/1610.02357.pdf
[https_arxiv.org_abs_1608.06993]: https://arxiv.org/abs/1608.06993
[https_arxiv.org_pdf_1704.04861.pdf]: https://arxiv.org/pdf/1704.04861.pdf
[https_arxiv.org_abs_1707.07012]: https://arxiv.org/abs/1707.07012
[http_arxiv.org_abs_1602.07360]: http://arxiv.org/abs/1602.07360
[https_arxiv.org_abs_1605.06211]: https://arxiv.org/abs/1605.06211
[https_arxiv.org_abs_1703.06211]: https://arxiv.org/abs/1703.06211
[http_arxiv.org_abs_1311.2524]: http://arxiv.org/abs/1311.2524
[https_arxiv.org_abs_1406.4729v2]: https://arxiv.org/abs/1406.4729v2
[https_arxiv.org_abs_1504.08083]: https://arxiv.org/abs/1504.08083
[https_arxiv.org_abs_1506.01497]: https://arxiv.org/abs/1506.01497
[https_arxiv.org_abs_1506.02640]: https://arxiv.org/abs/1506.02640
[https_arxiv.org_abs_1512.02325]: https://arxiv.org/abs/1512.02325
[https_arxiv.org_abs_1612.08242]: https://arxiv.org/abs/1612.08242
[https_arxiv.org_abs_1605.06409]: https://arxiv.org/abs/1605.06409
[https_arxiv.org_abs_1703.06870]: https://arxiv.org/abs/1703.06870
[https_arxiv.org_abs_1612.03144]: https://arxiv.org/abs/1612.03144
[https_arxiv.org_abs_1406.2661]: https://arxiv.org/abs/1406.2661
[http_arxiv.org_abs_1511.06434]: http://arxiv.org/abs/1511.06434
[https_arxiv.org_abs_1611.04076]: https://arxiv.org/abs/1611.04076
[https_arxiv.org_abs_1701.07875]: https://arxiv.org/abs/1701.07875
[https_arxiv.org_abs_1704.00028]: https://arxiv.org/abs/1704.00028
[https_arxiv.org_abs_1703.10717]: https://arxiv.org/abs/1703.10717
[https_arxiv.org_abs_1301.3781]: https://arxiv.org/abs/1301.3781
[https_arxiv.org_abs_1310.4546_NIPS]: https://arxiv.org/abs/1310.4546%EF%BC%8CNIPS
[https_arxiv.org_abs_1802.05365]: https://arxiv.org/abs/1802.05365
[https_arxiv.org_abs_1810.04805]: https://arxiv.org/abs/1810.04805
[https_arxiv.org_abs_1406.6247]: https://arxiv.org/abs/1406.6247
[https_arxiv.org_abs_1409.0473]: https://arxiv.org/abs/1409.0473
[https_arxiv.org_abs_1508.04025]: https://arxiv.org/abs/1508.04025
[https_arxiv.org_abs_1706.03762]: https://arxiv.org/abs/1706.03762