Going deeper with convolutions
Citations Over TimeTop 1% of 2015 papers
Abstract
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.
Related Papers
- → On the Role of Intuition in Decision Making and Some Ways of Multicriteria Aid of Intuition(1997)87 cited
- → Implementing convolutional neural network model for prediction in medical imaging(2022)6 cited
- → Do Leaders of Small and Medium‐Sized Businesses Base Decisions on Intuition? An Empirical Investigation Among West African Managers(2013)6 cited
- → On the Role of Intuition in Decision Making and Some Ways of Multicriteria Aid of Intuition(1997)5 cited
- On Editors' Intuition of Academic Journal(2001)