Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

Abstract

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly learning local and global features in a Convolutional Neural Network (CNN) by aiming to discover correlated local and global features in different context. Specifically, we formulate a method for joint learning of local and global feature selection losses designed to optimise person re-id when using only generic matching metrics such as the L2 distance. We design a novel CNN architecture for Jointly Learning Multi-Loss (JLML) of local and global discriminative feature optimisation subject concurrently to the same re-id labelled information. Extensive comparative evaluations demonstrate the advantages of this new JLML model for person re-id over a wide range of state-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03, Market-1501).

Accepted by IJCAI 2017

References in corpus (1)

• Person Re-Identification by Camera Correlation Aware Feature Augmentation

Cited by in corpus (6)

• Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
• PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• Meta Batch-Instance Normalization for Generalizable Person Re-Identification
• Symbiotic Adversarial Learning for Attribute-based Person Search
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN