• Corpus ID: 14124313

Very Deep Convolutional Networks for Large-Scale Image Recognition

@article{Simonyan2015VeryDC,
  title={Very Deep Convolutional Networks for Large-Scale Image Recognition},
  author={Karen Simonyan and Andrew Zisserman},
  journal={CoRR},
  year={2015},
  volume={abs/1409.1556}
}
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. [] Key Result We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
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.
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.
Tiny ImageNet Visual Recognition Challenge
TLDR
This work investigates the effect of convolutional network depth, receptive field size, dropout layers, rectified activation unit type and dataset noise on its accuracy in Tiny-ImageNet Challenge settings and achieves excellent performance even compared to state-of-the-art results.
Tiny ImageNet Visual Recognition Challenge
TLDR
This work tries to train a relatively deep network with a large number of filters per convolutional layer to achieve a high accuracy on the test dataset, and trains another classifier that is slightly shallower and has fewer number of parameters several times, to build a dataset that will allow for a thorough study of ensemble techniques.
On the Large-Scale Transferability of Convolutional Neural Networks
TLDR
This paper investigates the effective transfer of the CNN descriptors in generic and fine-grained classification at a large scale and provides some simple yet effective methods in constructing a competitive baseline recognition system.
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.
Striving for Simplicity: The All Convolutional Net
TLDR
It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.
Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition
TLDR
This study investigates various aspects of convolutional neural networks for visual concept recognition, and proposes efficient fusion mechanisms both for single and multiple network models.
Towards Good Practices for Very Deep Two-Stream ConvNets
TLDR
This report presents very deep two-stream ConvNets for action recognition, by adapting recent very deep architectures into video domain, and extends the Caffe toolbox into Multi-GPU implementation with high computational efficiency and low memory consumption.
Pre-trained CNNs as Visual Feature Extractors: A Broad Evaluation
TLDR
This work performs a wide-ranging evaluation of Convolutional Neural Networks as feature extractors for matching visual features under large changes in appearance, perspective, and visual scale, finding that the intermediate layers of DenseNets serve as the best feature extractor overall.
...
...

References

SHOWING 1-10 OF 59 REFERENCES
Going deeper with convolutions
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
Return of the Devil in the Details: Delving Deep into Convolutional Nets
TLDR
It is shown that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost, and it is identified that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance.
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.
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.
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.
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.
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
TLDR
This work designs a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset, and shows that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification.
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.
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.
Flexible, High Performance Convolutional Neural Networks for Image Classification
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a
...
...