Deep Person Re-Identification with Improved Embedding and Efficient Training

by   Haibo Jin, et al.

Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.


page 1

page 2

page 3

page 4


Support Neighbor Loss for Person Re-Identification

Person re-identification (re-ID) has recently been tremendously boosted ...

A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection

State-of-the-art person re-identification systems that employ a triplet ...

OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning

Deep neural networks trained using a softmax layer at the top and the cr...

Orthogonal Center Learning with Subspace Masking for Person Re-Identification

Person re-identification aims to identify whether pairs of images belong...

Writer Identification and Verification from Intra-variable Individual Handwriting

The handwriting of an individual may vary excessively with many factors ...

An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification

In recent years, a variety of proposed methods based on deep convolution...

Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

Person re-identification is to seek a correct match for a person of inte...

Please sign up or login with your details

Forgot password? Click here to reset