Going Deeper with Convolutions

Christian Szegedy1 , Wei Liu2 , Yangqing Jia1 , Pierre Sermanet1 , Scott Reed3 , Dragomir Anguelov1 , Dumitru Erhan1 , Vincent Vanhoucke1 , Andrew Rabinovich4 1Google Inc. 2University of North Carolina, Chapel Hill 3University of Michigan, Ann Arbor 4Magic Leap Inc. 1 {szegedy,jiayq,sermanet,dragomir,dumitru,vanhoucke}@google.com 2wliu@cs.unc.edu, 3reedscott@umich.edu, 4arabinovich@magicleap.com

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.