Rethinking the Inception Architecture for Computer Vision

CVPR 2016 Christian Szegedy • Vincent Vanhoucke • Sergey Ioffe • Jonathon Shlens • Zbigniew Wojna

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios.

Full paper



Task Dataset Model Metric name Metric value Global rank Compare
Image Classification ImageNet Inception V3 Top 1 Accuracy 78.8% # 11
Image Classification ImageNet Inception V3 Top 5 Accuracy 94.4% # 11