Papperoni

2015

Going Deeper With Convolutions

Christian Szegedy, Weizhou Liu, Y. Jia, P. Sermanet, S. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

Open PDF Google Scholar

citations

Cite Score

98

AI summary

This paper introduces the Inception architecture (GoogLeNet), a deep convolutional neural network that improves computational resource utilization. It achieved state-of-the-art results in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14) for both classification and detection, using fewer parameters than previous winning architectures.

Main Contributions

Introduces the Inception architecture, which improves the utilization of computing resources by carefully crafting a design that allows for increasing the depth and width of the network while keeping the computational budget constant.
Architectural decisions based on the Hebbian principle and the intuition of multi-scale processing.
Achieved state-of-the-art results for both classification and detection in the ILSVRC 2014.
GoogLeNet uses 12x fewer parameters than the winning architecture of Krizhevsky et al from two years prior, while being significantly more accurate.
Introduces auxiliary classifiers connected to intermediate layers to encourage discrimination in the lower stages of the classifier, increase the gradient signal that gets propagated back, and provide additional regularization.

Abstract

We propose a deep convolutional neural network architecture codenamed Inception, which was responsible for setting 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. This was achieved by a carefully crafted design that allows for increasing 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.

Citation Graph

Loading graph...

References [20]

Sort:

Filter:

[1]ImageNet Classification With Deep Convolutional Neural Networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton - 2012

71 papers in library cite

I'm giving this a 5 just because of the impact, but this is VEEERY derivative of earlier work. Kudos for them for putting it all together, but really there's nothing revolutionary here.

[2]Gradient-Based Learning Applied to Document Recognition

Yann Lecun, Leon Bottou, Yoshua Bengio, Patrick Haffner - 1998

62 papers in library cite

I absolutely hated this paper. Has ~50 pages but seems like 200 pages. Takes too long to explain some things that really is just repeating itself. Also doesn't seem to add too much on top of LeNet-5. Also, focuses a lot on GTNs, which really didn't stick.

[3]Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Ross Girshick, J. Donahue, Trevor Darrell, Jitendra Malik - 2014

18 papers in library cite

Good results, beat overfeat, used pretraining for improving performance. Only issue is that the paper is overly long...

[4]Visualizing and Understanding Convolutional Networks

Matthew D. Zeiler, Rob Fergus - 2014

15 papers in library cite

Very good explanation and visualization of CNNs, and also nice that they use their findings to improve the performance. The ablation study is also nice.

[5]Backpropagation Applied to Handwritten Zip-Code Recognition

Yann Lecun, B. Boser, John S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackal - 1989

24 papers in library cite

The first convolution NN! Very simple concept and very simply explained. Very good results and overall a good read.

[6]Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors

Geoffrey E. Hinton, N. Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov - 2012

25 papers in library cite

Dropout, super impactful. The idea that you are training many estimators at once is also very nice.

[7]Network in Network

M. Lin, Qinlang Chen, Shuicheng Yan - 2013

11 papers in library cite

I think this was badly written and explained. The idea is nice but I didn't like the paper at all.

[8]On the Importance of Initialization and Momentum in Deep Learning

Ilya Sutskever, James Martens, G. Dahl, Geoffrey Hinton - 2013

13 papers in library cite

They give very good context and it's easy to understand that they are doing this as a counterpoint to HF. Surprising results as well. I just think it was made obsolete by relu

[9]Large Scale Distributed Deep Networks

Jeffrey Dean, G. S. Corrado, R. Monga, K. Chen, M. Devin, Quoc V. Le, Mark Z. Mao, Marc'aurelio Ranzato, A. Senior, P. Tucker, K. Yang, Andrew Y. Ng - 2012

16 papers in library cite

Good paper, nice algorithm. Nothing too crazy, but I understand the impact. I think the work to create the system was larger than the algorithm itself.

[10]OverFeat: Integrated Recognition, Localization and Detection Using Convolutional Networks

P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, Rob Fergus, Yann Lecun - 2014

16 papers in library cite

Very convoluted method, was SotA for only a bit of time, and the paper is very boring.

[11]Some Improvements on Deep Convolutional Neural Network Based Image Classification

A. G. Howard - 2013

4 papers in library cite

CNNs with images of different scales

[12]Acceleration of Stochastic Approximation by Averaging

B. T. Polyak, A. B. Juditsky - 1992

4 papers in library cite

[13]Deep Neural Networks for Object Detection

Christian Szegedy, A. Toshev, Dumitru Erhan - 2013

4 papers in library cite

[14]Robust Object Recognition With Cortex-Like Mechanisms

T. Serre, Lior Wolf, S. Bileschi, M. Riesenhuber, T. Poggio - 2007

4 papers in library cite

[15]Scalable Object Detection Using Deep Neural Networks

Dumitru Erhan, Christian Szegedy, A. Toshev, Dragomir Anguelov - 2014

4 papers in library cite

[16]Segmentation as Selective Search for Object Recognition

K. E. A. V. D. Sande, J. R. R. Uijlings, T. Gevers, A. W. M. Smeulders - 2011

3 papers in library cite

[17]Deeppose: Human Pose Estimation via Deep Neural Networks

A. Toshev, Christian Szegedy - 2014

2 papers in library cite

[18]On Two-Dimensional Sparse Matrix Partitioning: Models, Methods, and a Recipe

U. V. Catalyurek, C. Aykanat, B. Ucar - 2010

1 paper in library cites

[19]Provable Bounds for Learning Some Deep Representations

S. Arora, A. Bhaskara, R. Ge, T. Ma - 2013

1 paper in library cites

[20]Scaling Up Matrix Computations on Shared-Memory Manycore Systems With 1000 CPU Cores

Francis Song, J. Dongarra - 2014

1 paper in library cites

Cited by

20

papers in your library

Cites

11

papers in your library

Read

on July 22, 2025

Introduced the inception algorithm, which is nice. The paper is quite good, but I had to google some stuff to understand it fully. Nice contribution and SotA, but TBH I felt that it wasn't toooo good of a read.

Tags

Paper Aliases

No aliases