Convolutional Neural Networks Learn Compact Local Image Descriptors

We investigate if a deep Convolutional Neural Network can learn representations of local image patches that are usable in the important task of keypoint matching. We examine several possible loss functions for this correspondance task and show emprically that a newly suggested loss formulation allows a Convolutional Neural Network to find compact local image descriptors that perform comparably to state-of-the-art approaches.

[1]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[2]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[4]  Andrew Zisserman,et al.  Descriptor Learning Using Convex Optimisation , 2012, ECCV.

[5]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Vincent Lepetit,et al.  Learning Image Descriptors with the Boosting-Trick , 2012, NIPS.

[8]  Geoffrey E. Hinton,et al.  Self-organizing neural network that discovers surfaces in random-dot stereograms , 1992, Nature.

[9]  Roberto Cipolla,et al.  Semantic texton forests for image categorization and segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Yann LeCun,et al.  Learning long-range vision for an offroad robot , 2008 .

[12]  Gang Hua,et al.  Discriminative Learning of Local Image Descriptors , 1990, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Sven Behnke,et al.  Learning Object-Class Segmentation with Convolutional Neural Networks , 2012, ESANN.

[14]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[15]  Horst Bischof,et al.  Learned local descriptors for recognition and matching , 2008 .