Rethinking the Inception Architecture for Computer Vision

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2818 - 2826
• Main Authors: Szegedy, Christian, Vanhoucke, Vincent, Ioffe, Sergey, Shlens, Jon, Wojna, Zbigniew
• Format: Conference Proceeding
• Language: English
• Published: IEEE 09.12.2016
• Subjects: Benchmark testing; Computational efficiency; Computational modeling; Computer architecture; Computer vision; Convolution; Training

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...