Imagenet classification with deep convolutional neural networks

Caffe: Convolutional architecture for fast feature embedding

Y Jia, E Shelhamer, J Donahue, S Karayev… - Proceedings of the …, 2014 - dl.acm.org
Abstract Caffe provides multimedia scientists and practitioners with a clean and modifiable
framework for state-of-the-art deep learning algorithms and a collection of reference models.
The framework is a BSD-licensed C++ library with Python and MATLAB bindings for ...

Rich feature hierarchies for accurate object detection and semantic segmentation

R Girshick, J Donahue, T Darrell… - Proceedings of the IEEE …, 2014 - cv-foundation.org
Abstract Object detection performance, as measured on the canonical PASCAL VOC
dataset, has plateaued in the last few years. The best-performing methods are complex
ensemble systems that typically combine multiple low-level image features with high-level ...

Very deep convolutional networks for large-scale image recognition

K Simonyan, A Zisserman - arXiv preprint arXiv:1409.1556, 2014 - arxiv.org
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) ...

Representation learning: A review and new perspectives

Y Bengio, A Courville, P Vincent - IEEE transactions on pattern …, 2013 - ieeexplore.ieee.org
Abstract—The success of machine learning algorithms generally depends on data
representation, and we hypothesize that this is because different representations can
entangle and hide more or less the different explanatory factors of variation behind the ...

Going deeper with convolutions

C Szegedy, W Liu, Y Jia, P Sermanet… - Proceedings of the …, 2015 - cv-foundation.org
Abstract 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 (ILSVRC2014). The main ...

Visualizing and understanding convolutional networks

MD Zeiler, R Fergus - European Conference on Computer Vision, 2014 - Springer
Abstract Large Convolutional Network models have recently demonstrated impressive
classification performance on the ImageNet benchmark Krizhevsky et al.[18]. However there
is no clear understanding of why they perform so well, or how they might be improved. In ...

Imagenet large scale visual recognition challenge

O Russakovsky, J Deng, H Su, J Krause… - International Journal of …, 2015 - Springer
Abstract The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object
category classification and detection on hundreds of object categories and millions of
images. The challenge has been run annually from 2010 to present, attracting ...

[PDF][PDF] Dropout: a simple way to prevent neural networks from overfitting.

N Srivastava, GE Hinton, A Krizhevsky… - Journal of Machine …, 2014 - jmlr.org
Abstract Deep neural nets with a large number of parameters are very powerful machine
learning systems. However, overfitting is a serious problem in such networks. Large
networks are also slow to use, making it difficult to deal with overfitting by combining the ...

Overfeat: Integrated recognition, localization and detection using convolutional networks

P Sermanet, D Eigen, X Zhang, M Mathieu… - arXiv preprint arXiv: …, 2013 - arxiv.org
Abstract: We present an integrated framework for using Convolutional Networks for
classification, localization and detection. We show how a multiscale and sliding window
approach can be efficiently implemented within a ConvNet. We also introduce a novel ...

[PDF][PDF] DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition.

J Donahue, Y Jia, O Vinyals, J Hoffman, N Zhang… - ICML, 2014 - jmlr.org
Abstract We evaluate whether features extracted from the activation of a deep convolutional
network trained in a fully supervised fashion on a large, fixed set of object recognition tasks
can be repurposed to novel generic tasks. Our generic tasks may differ significantly from ...

Create alert