Scalable Person Re-identification on Supervised Smoothed Manifold
Citations Over TimeTop 1% of 2017 papers
Abstract
Most existing person re-identification algorithms either extract robust visual features or learn discriminative metrics for person images. However, the underlying manifold which those images reside on is rarely investigated. That arises a problem that the learned metric is not smooth with respect to the local geometry structure of the data manifold. In this paper, we study person re-identification with manifold-based affinity learning, which did not receive enough attention from this area. An unconventional manifold-preserving algorithm is proposed, which can 1) make best use of supervision from training data, whose label information is given as pairwise constraints, 2) scale up to large repositories with low on-line time complexity, and 3) be plunged into most existing algorithms, serving as a generic postprocessing procedure to further boost the identification accuracies. Extensive experimental results on five popular person re-identification benchmarks consistently demonstrate the effectiveness of our method. Especially, on the largest CUHK03 and Market-1501, our method outperforms the state-of-the-art alternatives by a large margin with high efficiency, which is more appropriate for practical applications.
Related Papers
- → Multi-manifold LLE learning in pattern recognition(2015)74 cited
- A General Framework for Manifold Alignment(2009)
- Manifold learning and manifold alignment based on coupled linear projections(2010)
- → Multiple Manifold Learning by Nonlinear Dimensionality Reduction(2011)10 cited
- → A Fast Manifold Learning Algorithm for Dimensionality Reduction(2016)1 cited