Going deeper with convolutions

@article{Szegedy2015GoingDW,
  title={Going deeper with convolutions},
  author={Christian Szegedy and W. Liu and Y. Jia and Pierre Sermanet and Scott E. Reed and Dragomir Anguelov and D. Erhan and V. Vanhoucke and Andrew Rabinovich},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={1-9}
}
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… Expand
View on IEEE
arxiv.org
25,635 Citations
Highly Influential Citations
3,131
Background Citations
8,547
Methods Citations
8,735
Results Citations
263

Supplemental Content

Github Repo
Via Papers with Code
marload/ConvNets-TensorFlow2
⛵️ Implementation a variety of popular Image Classification Models using TensorFlow2. [ResNet, GoogLeNet, VGG, Inception-v3, Inception-v4, MobileNet, MobileNet-v2, ShuffleNet, ShuffleNet-v2, etc...]
41 Stars • 10 Forks
Datasets
ImageNet
21:59
Video
GoogLeNet Tutorial
auro tripathy
4 January 2017

25,635 Citations

Citation Type

Citation Type

Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification
  • H. Ergun, M. Sert
  • Computer Science
  • 2016 IEEE Second International Conference on Multimedia Big Data (BigMM)
  • 2016
TLDR
This study investigates various aspects of convolutional neural networks (CNNs) from the big data perspective, and proposes efficient fusion mechanisms both for single and multiple network models. Expand
CPWC: Contextual Point Wise Convolution for Object Recognition
TLDR
This work proposes an alternative design for pointwise convolution, which uses spatial information from the input efficiently and significantly improves the performance of the networks without substantially increasing the number of parameters and computations. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
A CONVblock for Convolutional Neural Networks
TLDR
The main objective of this architecture is to improve the main performances of the network thanks to a new design based on CONVblock, and demonstrates the effectiveness of the proposed method. Expand
DecomposeMe: Simplifying ConvNets for End-to-End Learning
TLDR
DecomposeMe, a simple but effective technique to learn features using 1D convolutions using an architecture that requires 92% fewer parameters compared to VGG-B, is proposed. Expand
Convolutional Neural Network for Image Feature Extraction Based on Concurrent Nested Inception Modules
TLDR
A new architecture based on Inception module is proposed, which helps the net build a more comprehensive cognition on the image and get great performance. Expand
Gradually Updated Neural Networks for Large-Scale Image Recognition
TLDR
An alternative method to increase the depth of neural networks by introducing computation orderings to the channels within convolutional layers or blocks, based on which the outputs are gradually computed in a channel-wise manner. Expand
A fast , implementation of a deep vanilla
  • 2016
Introduction During the past few years, convolutional neural networks (CNNs) have been established as the dominant technology for approaching real-world visual understanding tasks. A significant… Expand
An Architecture to Accelerate Convolution in Deep Neural Networks
TLDR
This paper proposes an efficient computational method, which is inspired by a computational core of fully connected neural networks, to process convolutional layers of state-of-the-art deep CNNs within strict latency requirements, and implemented its method customized for VGG and VGG-based networks which have shown state of theart performance on different classification/recognition data sets. Expand
Deep convolutional neural networks as generic feature extractors
TLDR
These findings indicate that convolutional networks are able to learn generic feature extractors that can be used for different tasks, and also indicate that the long time needed to train such deep networks is a major drawback. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 278 REFERENCES
Some Improvements on Deep Convolutional Neural Network Based Image Classification
TLDR
This paper summarizes the entry in the Imagenet Large Scale Visual Recognition Challenge 2013, which achieved a top 5 classification error rate and achieved over a 20% relative improvement on the previous year's winner. Expand
Scalable Object Detection Using Deep Neural Networks
TLDR
This work proposes a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest. Expand
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TLDR
DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms. Expand
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks. Expand
Visualizing and Understanding Convolutional Networks
TLDR
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. Expand
Network In Network
TLDR
With enhanced local modeling via the micro network, the proposed deep network structure NIN is able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Multi-scale Orderless Pooling of Deep Convolutional Activation Features
TLDR
A simple but effective scheme called multi-scale orderless pooling (MOP-CNN), which extracts CNN activations for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. Expand
Two-Stream Convolutional Networks for Action Recognition in Videos
TLDR
This work proposes a two-stream ConvNet architecture which incorporates spatial and temporal networks and demonstrates that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Expand
Deep Neural Networks for Object Detection
TLDR
This paper presents a simple and yet powerful formulation of object detection as a regression problem to object bounding box masks, and defines a multi-scale inference procedure which is able to produce high-resolution object detections at a low cost by a few network applications. Expand
...
1
2
3
4
5
...