Issue No. 08 - Aug. (2014 vol. 36)
Karen Simonyan , Visual Geometry Group, Department of Engineering Science, University of Oxford, Oxford, United Kingdom
Andrea Vedaldi , Visual Geometry Group, Department of Engineering Science, University of Oxford, Oxford, United Kingdom
Andrew Zisserman , Visual Geometry Group, Department of Engineering Science, University of Oxford, Oxford, United Kingdom
The objective of this work is to learn descriptors suitable for the sparse feature detectors used in viewpoint invariant matching. We make a number of novel contributions towards this goal. First, it is shown that learning the pooling regions for the descriptor can be formulated as a convex optimisation problem selecting the regions using sparsity. Second, it is shown that descriptor dimensionality reduction can also be formulated as a convex optimisation problem, using Mahalanobis matrix nuclear norm regularisation. Both formulations are based on discriminative large margin learning constraints. As the third contribution, we evaluate the performance of the compressed descriptors, obtained from the learnt real-valued descriptors by binarisation. Finally, we propose an extension of our learning formulations to a weakly supervised case, which allows us to learn the descriptors from unannotated image collections. It is demonstrated that the new learning methods improve over the state of the art in descriptor learning on the annotated local patches data set of Brown et al.
and unannotated photo collections of Philbin et al. .
Optimization, Vectors, Training, Image retrieval, Robustness, Detectors, Feature extraction,image retrieval, Descriptor learning, feature descriptor, binary descriptor, dimensionality reduction, sparsity, nuclear norm, trace norm, feature matching
Karen Simonyan, Andrea Vedaldi, Andrew Zisserman, "Learning Local Feature Descriptors Using Convex Optimisation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 36, no. , pp. 1573-1585, Aug. 2014, doi:10.1109/TPAMI.2014.2301163