Open AccessProceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
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.Abstract:
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. 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.read more
Citations
More filters
Journal ArticleDOI
Deep packet: a novel approach for encrypted traffic classification using deep learning
Mohammad Lotfollahi,Mahdi Jafari Siavoshani,Ramin Shirali Hossein Zade,Mohammdsadegh Saberian +3 more
TL;DR: Deep Packet can identify encrypted traffic and also distinguishes between VPN and non-VPN network traffic, and outperforms all of the proposed classification methods on UNB ISCX VPN-nonVPN dataset.
Posted Content
Mixed Precision Training
Paulius Micikevicius,Sharan Narang,Jonah M. Alben,Gregory Diamos,Erich Elsen,David Garcia,Boris Ginsburg,Michael J. Houston,Oleksii Kuchaiev,Ganesh Venkatesh,Hao Wu +10 more
TL;DR: In this paper, a technique to train deep neural networks using half-precision floating point numbers is introduced. But the authors do not address the memory and compute requirements for training these models and propose two techniques to handle this loss of information.
Proceedings Article
All you need is a good init
Dmytro Mishkin,Jiri Matas +1 more
TL;DR: Performance is evaluated on GoogLeNet, CaffeNet, FitNets and Residual nets and the state-of-the-art, or very close to it, is achieved on the MNIST, CIFAR-10/100 and ImageNet datasets.
Proceedings ArticleDOI
Pre-Trained Image Processing Transformer
Hanting Chen,Yunhe Wang,Tianyu Guo,Chang Xu,Yiping Deng,Zhenhua Liu,Siwei Ma,Chunjing Xu,Chao Xu,Wen Gao +9 more
TL;DR: Hu et al. as discussed by the authors proposed a pre-trained image processing transformer (IPT) model for denoising, super-resolution and deraining tasks, which is trained on corrupted image pairs with multi-heads and multi-tails.
Journal ArticleDOI
The THUMOS challenge on action recognition for videos “in the wild”
Haroon Idrees,Amir Roshan Zamir,Yu-Gang Jiang,Alexander Gorban,Ivan Laptev,Rahul Sukthankar,Mubarak Shah +6 more
TL;DR: The THUMOS benchmark is described in detail and an overview of data collection and annotation procedures are given, including a comprehensive empirical study evaluating the differences in action recognition between trimmed and untrimed videos, and how well methods trained on trimmed videos generalize to untrimmed videos.
References
More filters
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Posted Content
Fully Convolutional Networks for Semantic Segmentation
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Journal ArticleDOI
Backpropagation applied to handwritten zip code recognition
Yann LeCun,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +6 more
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Journal ArticleDOI
The Pascal Visual Object Classes Challenge: A Retrospective
TL;DR: A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.