Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification

Citations Over TimeTop 10% of 2017 papers

Abstract

We propose Multi-Task Learning with Low Rank Attribute Embedding (MTL-LORAE) to address the problem of person re-identification on multi-cameras. Re-identifications on different cameras are considered as related tasks, which allows the shared information among different tasks to be explored to improve the re-identification accuracy. The MTL-LORAE framework integrates low-level features with mid-level attributes as the descriptions for persons. To improve the accuracy of such description, we introduce the low-rank attribute embedding, which maps original binary attributes into a continuous space utilizing the correlative relationship between each pair of attributes. In this way, inaccurate attributes are rectified and missing attributes are recovered. The resulting objective function is constructed with an attribute embedding error and a quadratic loss concerning class labels. It is solved by an alternating optimization strategy. The proposed MTL-LORAE is tested on four datasets and is validated to outperform the existing methods with significant margins.

Related Papers

• → Embedding as a modeling problem(1998)167 cited
• → PixelSNE: Pixel‐Aligned Stochastic Neighbor Embedding for Efficient 2D Visualization with Screen‐Resolution Precision(2018)2 cited
• → A solution to the reversible embedding problem for finite Markov chains(2016)2 cited
• → A reversible and multiple-layer embedding strategy with high capacity(2010)