2015 GoingDeeperwithConvolutions
- (Szegedy et al., 2015) ⇒ Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. (2014, 2015). “Going Deeper with Convolutions.” In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR.2015.7298594
Subject Headings: Convolutional Neural Network; GoogLeNet; Deep Learning Neural Network.
Notes
- An e-print version (arXiv:1409.4842) of this articles was initially publoshed in 2014.
Cited By
Quotes
Author Keywords
- Computer architecture; Convolutional codes; Sparse matrices; Neural networks; Visualization; Object detection; Computer vision
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.
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2015 GoingDeeperwithConvolutions | Wei Liu Dumitru Erhan Pierre Sermanet Christian Szegedy Yangqing Jia Dragomir Anguelov Vincent Vanhoucke Andrew Rabinovich Scott E. Reed | Going Deeper with Convolutions | 10.1109/CVPR.2015.7298594 | 2015 |