1. NIPS-2012,Alexnet:深度学习CV领域划时代论文,具有里程碑意义
《ImageNet Classification with Deep Convolutional Neural Networks》
2. ICLR-2015,VGG net:开启3*3卷积堆叠时代
《Very Deep Convolutional Networks for Large-Scale Image Recognition》
3. CVPR-2015,googlenet v1:Google系列论文开创论文,提出多尺度卷积模块《Going deeper with convolutions》
4. arXiv-2015,googlenet v2: 神经网络大杀器:BN层提出
《Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift》
5. CVPR-2016,googlenet v3: 卷积分解及结构进化,超越人类精度
《Rethinking the Inception Architecture for Computer Vision》
6. CVPR-2016,resnet:工业界标杆模型,最具影响力的卷积神经网络
《Deep Residual Learning for Image Recognition》
7. arXiv-2016,googlenet v4: Inception与ResNet结构的尝试
《 Inception-ResNet and the Impact of Residual Connections on Learning》
8. CVPR-2017,ResNeXt:何恺明团队对ResNet重大改进
《Aggregated Residual Transformations for Deep Neural Networks》
9. CVPR-2017,densenet:ResNet的改进,2016-ILSVRC冠军
《Densely Connected Convolutional Networks》
10. TPAMI-2017,SEnet:引入注意力机制的卷积神经网络,2017-ILSVRC(最后一届)冠军
《Squeeze-and-Excitation Networks》