2016

PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors

Balntas, Vassileios, Johns, Edward, Tang, Lilian et al.

Understand

In this paper we propose a new approach for learning local descriptors for matching image patches.

It has recently been demonstrated that descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance.
Unfortunately their computational complexity is prohibitive for any practical application.
We address this problem and propose a CNN based descriptor with improved matching performance, significantly reduced training and execution time, as well as low dimensionality.

A performance evaluation of local descriptors
K. Mikolajczyk and C. Schmid · 2003
Earlier work this paper cites.
Distinctive image features from scale-invariant keypoints
D. G. Lowe · 2004
Earlier work this paper cites.
Scale and affine invariant interest point detectors
K. Mikolajczyk and C. Schmid · 2004
Earlier work this paper cites.
Workshop on Edge Computing Using New Commodity Architectures. 2006
S. Sinha, J.M. Frahm, M. Pollefeys and Y. Genc · 2006
Earlier work this paper cites.
Dimensionality reduction by learning an invariant mapping
R. Hadsell, S. Chopra, and Y. LeCun · 2006
Earlier work this paper cites.
Picking the best daisy
S. Winder, G. Hua, and M. Brown · 2009
Earlier work this paper cites.
A survey on metric learning for feature vectors and structured data
M. S. Aurélien Bellet, Amaury Habrard · 2010
Earlier work this paper cites.
BRIEF: Binary Robust Independent Elementary Features
M. Calonder, V. Lepetit, C. Strecha, and P. Fua · 2010
Earlier work this paper cites.
Object detection with discriminatively trained part based models
P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan · 2010
Earlier work this paper cites.

Torch7: A matlab-like environment for machine learning
R. Collobert, K. Kavukcuoglu, and C. Farabet · 2011
Cited alongside, same era.
Discriminative learning of local image descriptors
G. H. M. Brown and S. Winder · 2011
Cited alongside, same era.
Stochastic gradient tricks
L. Bottou · 2012
Cited alongside, same era.
CUDNN: Efficient primitives for deep learning
S. Chetlur, C. Woolley, P. Vandermersch, J. Cohen, J. Tran, B. Catanzaro, and E. Shelhamer · 2014
Cited alongside, same era.
Descriptor matching with convolutional neural networks: a comparison to sift
P. Fischer, A. Dosovitskiy, and T. Brox · 2014
Cited alongside, same era.
Deep metric learning using triplet network
E. Hoffer and N. Ailon · 2014
Cited alongside, same era.
Learning local feature descriptors using convex optimisation
K. Simonyan, A. Vedaldi, and A. Zisserman · 2014
Cited alongside, same era.
Learning fine grained image similarity with deep ranking
J. Wang, Y. Song, T. Leung, C. Rosenberg, J. Wang, J. Philbin, B. Chen, and Y. Wu · 2014
Cited alongside, same era.

Domain-size pooling in local descriptors: DSP-SIFT
J. Dong and S. Soatto · 2015
Later among the works it cites.
Matchnet: Unifying feature and metric learning for patch-based matching
X. Han, T. Leung, Y. Jia, R. Sukthankar, and A. C. Berg · 2015
Later among the works it cites.
P-n learning: Bootstrapping binary classifiers by structural constraints
Z. Kalal, J. Matas, and K. Mikolajczyk · 2015
Later among the works it cites.
Deep learning
Y. LeCun, Y. Bengio, and G. Hinton · 2015
Later among the works it cites.
ImageNet Large Scale Visual Recognition Challenge
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei · 2015
Later among the works it cites.
Discriminative learning of deep convolutional feature point descriptors
E. Simo-Serra, E. Trulls, L. Ferraz, I. Kokkinos, P. Fua, and F. Moreno-Noguer · 2015
Later among the works it cites.
Learning Descriptors for Object Recognition and 3D Pose Estimation
P. Wohlhart and V. Lepetit · 2015
Later among the works it cites.
Learning to compare image patches via convolutional neural networks
S. Zagoruyko and N. Komodakis · 2015
Later among the works it cites.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…