Results 1 - 10 of 75

Return of the Devil in the Details: Delving Deep into Convolutional Nets

by Ken Chatfield, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman , 2014
"... The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in chal-lenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compar ..."
Abstract - Cited by 71 (8 self) - Add to MetaCart
The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in chal-lenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods

Part Detector Discovery in Deep Convolutional Neural Networks

by Marcel Simon, Erik Rodner, Joachim Denzler
"... Abstract. Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature represen-tations suitable for discrimination. However, part localization is a chal-lenging task due to the large variation of appearance and pose. In this paper, ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
, we show how pre-trained convolutional neural networks can be used for robust and efficient object part discovery and localization with-out the necessity to actually train the network on the current dataset. Our approach called “part detector discovery ” (PDD) is based on ana-lyzing the gradient maps

Going deeper with convolutions

by Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich , 2014
"... We propose a deep convolutional neural network architecture codenamed Incep-tion, which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improv ..."
Abstract - Cited by 65 (2 self) - Add to MetaCart
We propose a deep convolutional neural network architecture codenamed Incep-tion, which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture

Using Genetic Variation and Environmental Risk Factor Data to Identify Individuals at High Risk for Age-Related Macular Degeneration

by Kylee L. Spencer, Lana M. Olson, Nathalie Schnetz-boutaud, Paul Gallins, Anita Agarwal, Ro Iannaccone, Stephen B. Kritchevsky, Melissa Garcia, Michael A. Nalls, Anne B, William K. Scott, Margaret A. Pericak-vance, Jonathan L. Haines
"... A major goal of personalized medicine is to pre-symptomatically identify individuals at high risk for disease using knowledge of each individual’s particular genetic profile and constellation of environmental risk factors. With the identification of several well-replicated risk factors for age-relat ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
A major goal of personalized medicine is to pre-symptomatically identify individuals at high risk for disease using knowledge of each individual’s particular genetic profile and constellation of environmental risk factors. With the identification of several well-replicated risk factors for age-related

Scalable object detection using deep neural networks

by Dumitru Erhan, Christian Szegedy, Er Toshev, Dragomir Anguelov - University of Tennessee, Knoxville
"... Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the localization sub-task was a net-work that predicts a single boun ..."
Abstract - Cited by 22 (2 self) - Add to MetaCart
Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the localization sub-task was a net-work that predicts a single

Spatial pyramid pooling in deep convolutional networks for visual recognition

by Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun - In ECCV
"... Abstract. Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g. 224×224) input image. This requirement is “artificial” and may hurt the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with a more principled poo ..."
Abstract - Cited by 52 (5 self) - Add to MetaCart
Abstract. Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g. 224×224) input image. This requirement is “artificial” and may hurt the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with a more principled

Age and Gender Classification Using Convolutional Neural Networks

by Gil Levi, Tal Hassner - In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015
"... Automatic age and gender classification has become rel-evant to an increasing amount of applications, particularly since the rise of social platforms and social media. Nev-ertheless, performance of existing methods on real-world images is still significantly lacking, especially when com-pared to the ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
-pared to the tremendous leaps in performance recently re-ported for the related task of face recognition. In this paper we show that by learning representations through the use of deep-convolutional neural networks (CNN), a significant increase in performance can be obtained on these tasks. To this end, we propose a

Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

by Alessandro Giusti, Dan C. Cire¸san, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber, Alessandro Giusti, Dan C. Cire¸san, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber , 2013
"... Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dynamic programming can speedup the process by o ..."
Abstract - Cited by 11 (0 self) - Add to MetaCart
Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dynamic programming can speedup the process

FAST IMAGE SCANNINGWITH DEEP MAX-POOLING CONVOLUTIONAL NEURAL NETWORKS

by Ro Giusti, Dan C. Cireşan, Jonathan Masci, Luca M. Gambardella
"... Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dy-namic programming can speedup the process by ..."
Abstract - Add to MetaCart
Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dy-namic programming can speedup the process

DeepBox: Learning Objectness with Convolutional Networks

by Weicheng Kuo, Bharath Hariharan, Jitendra Malik
"... Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that “objectness ” is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object propos-als. Our framework, which we call DeepBox, uses convo-lutional neural net ..."
Abstract - Add to MetaCart
Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that “objectness ” is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object propos-als. Our framework, which we call DeepBox, uses convo-lutional neural
Results 1 - 10 of 75