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
Cross Modal Distillation for Supervision Transfer
TL;DR: This work uses learned representations from a large labeled modality as supervisory signal for training representations for a new unlabeled paired modality and can be used as a pre-training procedure for new modalities with limited labeled data.
Posted Content
Learning with a Strong Adversary
TL;DR: A new and simple way of finding adversarial examples is presented and experimentally shown to be efficient and greatly improves the robustness of the classification models produced.
Journal ArticleDOI
Visual Saliency Detection Based on Multiscale Deep CNN Features
Guanbin Li,Yizhou Yu +1 more
TL;DR: This paper discovers that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks.
Proceedings ArticleDOI
Fast ConvNets Using Group-Wise Brain Damage
Vadim Lebedev,Victor Lempitsky +1 more
TL;DR: The idea of brain damage is revisit, i.e. the pruning of the coefficients of a neural network is suggested, and how brain damage can be modified and used to speedup convolutional layers in ConvNets is suggested.
Proceedings ArticleDOI
DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications
TL;DR: This paper proposes DeepMon, a mobile deep learning inference system to run a variety of deep learning inferences purely on a mobile device in a fast and energy-efficient manner and designs a suite of optimization techniques to efficiently offload convolutional layers to mobile GPUs and accelerate the processing.
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.