DeepAI AI Chat
Log In Sign Up

Implicit Sample Extension for Unsupervised Person Re-Identification

by   Xinyu Zhang, et al.

Most existing unsupervised person re-identification (Re-ID) methods use clustering to generate pseudo labels for model training. Unfortunately, clustering sometimes mixes different true identities together or splits the same identity into two or more sub clusters. Training on these noisy clusters substantially hampers the Re-ID accuracy. Due to the limited samples in each identity, we suppose there may lack some underlying information to well reveal the accurate clusters. To discover these information, we propose an Implicit Sample Extension () method to generate what we call support samples around the cluster boundaries. Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy. PLI controls the generation with two critical factors, i.e., 1) the direction from the actual sample towards its K-nearest clusters and 2) the degree for mixing up the context information from the K-nearest clusters. Meanwhile, given the support samples, ISE further uses a label-preserving loss to pull them towards their corresponding actual samples, so as to compact each cluster. Consequently, ISE reduces the "sub and mixed" clustering errors, thus improving the Re-ID performance. Extensive experiments demonstrate that the proposed method is effective and achieves state-of-the-art performance for unsupervised person Re-ID. Code is available at: <>.


page 1

page 2

page 3

page 4


Cluster Contrast for Unsupervised Person Re-Identification

Unsupervised person re-identification (re-ID) attractsincreasing attenti...

Progressive Cluster Purification for Unsupervised Feature Learning

In unsupervised feature learning, sample specificity based methods ignor...

Energy Clustering for Unsupervised Person Re-identification

Due to the high cost of data annotation in supervised learning for perso...

Part-based Pseudo Label Refinement for Unsupervised Person Re-identification

Unsupervised person re-identification (re-ID) aims at learning discrimin...

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

Recently, many approaches tackle the Unsupervised Domain Adaptive person...

AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification

Domain adaptive person re-identification (re-ID) is a challenging task, ...

Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

Person re-identification aims to establish the correct identity correspo...