Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

23 Feb 2016Christian Szegedy • Sergey Ioffe • Vincent Vanhoucke • Alex Alemi

Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performance in the 2015 ILSVRC challenge; its performance was similar to the latest generation Inception-v3 network. Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. We also present several new streamlined architectures for both residual and non-residual Inception networks.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Image Classification ImageNet Inception ResNet V2 Top 1 Accuracy 80.1% # 8
Image Classification ImageNet Inception ResNet V2 Top 5 Accuracy 95.1% # 8