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).

arXiv commentAccepted by IJCAI 2017

References in corpus (1)

• Person Re-Identification by Camera Correlation Aware Feature Augmentation

Cited by in corpus (18)

• Second-order Non-local Attention Networks for Person Re-identification
• The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
• Discriminative Feature Learning with Foreground Attention for Person Re-Identification
• Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
• Meta Batch-Instance Normalization for Generalizable Person Re-Identification
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• Person Re-identification Using Visual Attention
• Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
• HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
• In Defense of the Classification Loss for Person Re-Identification
• Symbiotic Adversarial Learning for Attribute-based Person Search
• Cross-dataset Person Re-Identification Using Similarity Preserved Generative Adversarial Networks
• Progressive Learning Algorithm for Efficient Person Re-Identification
• Nonlinear Collaborative Scheme for Deep Neural Networks
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN