Open AccessProceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
Reads0
Chats0
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
Posted Content
Convolutional Pose Machines
TL;DR: This work designs a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference in structured prediction tasks such as articulated pose estimation.
Posted Content
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
TL;DR: In this paper, a combination of deep and shallow, fully convolutional networks is used to predict the density map for a given crowd image, which is used for effectively capturing both the high-level semantic information (face/body detectors) and the low-level features (blob detectors), that are necessary for crowd counting under large scale variations.
Book ChapterDOI
Brain Tumor Classification Using Convolutional Neural Network
TL;DR: This study attempted to train a Convolutional Neural Network to recognize the three most common types of brain tumors, i.e. the Glioma, Meningiomas, and Pituitary, using the simplest possible architecture.
Journal ArticleDOI
HDR image reconstruction from a single exposure using deep CNNs
TL;DR: In this article, a deep convolutional neural network (CNN) is proposed to predict information that has been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure.
Journal ArticleDOI
Deep convolutional neural network model based chemical process fault diagnosis
Hao Wu,Jinsong Zhao +1 more
TL;DR: A fault diagnosis method based on a DCNN model consisting of convolutional layers, pooling layers, dropout, fully connected layers is proposed for chemical process fault diagnosis and the benchmark Tennessee Eastman (TE) process is utilized to verify the outstanding performance.
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.