Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
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.
Cited by 45,832 works. doi:10.1109/cvpr.2015.7298594
Authors
- Christian Szegedy
- Wei Liu
- Yangqing Jia
- Pierre Sermanet
- Scott Reed
- Dragomir Anguelov
- Dumitru Erhan
- Vincent Vanhoucke
- Andrew Rabinovich
References
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Backpropagation Applied to Handwritten Zip Code Recognition
- Improving neural networks by preventing co-adaptation of feature detectors
- Visualizing and Understanding Convolutional Networks
- Large Scale Distributed Deep Networks
- On the importance of initialization and momentum in deep learning
- Network In Network
- Scalable Object Detection Using Deep Neural Networks