Scalable Person Re-identification on Supervised Smoothed Manifold

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 raises 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 the 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.

Accepted as spotlight by CVPR 2017

Cited by in corpus (8)

• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
• Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
• Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping
• Efficient Pipelines for Vision-Based Context Sensing