Going deeper with convolutions

• Published in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1 - 9
• Main Authors: Szegedy, Christian, Wei Liu, Yangqing Jia, Sermanet, Pierre, Reed, Scott, Anguelov, Dragomir, Erhan, Dumitru, Vanhoucke, Vincent, Rabinovich, Andrew
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2015
• Subjects: Architecture (computers); Classification; Computation; Computer architecture; Computer vision; Conferences; Constants; Convolutional codes; Networks; Neural networks; Object detection; Pattern recognition; Sparse matrices; Visualization
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2015.7298594

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.