Log In Sign Up

Cluster Contrast for Unsupervised Person Re-Identification

by   Zuozhuo Dai, et al.

Unsupervised person re-identification (re-ID) attractsincreasing attention due to its practical applications in in-dustry. State-of-the-art unsupervised re-ID methods trainthe neural networks using a memory-based non-parametricsoftmax loss. They store the pre-computed instance featurevectors inside the memory, assign pseudo labels to them us-ing clustering algorithm, and compare the query instancesto the cluster using a form of contrastive loss. Duringtraining, the instance feature vectors are updated. How-ever, due to the varying cluster size, the updating progressfor each cluster is inconsistent. To solve this problem, wepresent Cluster Contrast which stores feature vectors andcomputes contrast loss in the cluster level. We demonstratethat the inconsistency problem for cluster feature represen-tation can be solved by the cluster-level memory dictionary.By straightforwardly applying Cluster Contrast to a stan-dard unsupervised re-ID pipeline, it achieves considerableimprovements of 9.5 purely unsupervised re-ID methods and 5.1 state-of-the-art unsuperviseddomain adaptation re-ID methods on the Market, Duke, andMSMT17 datasets.Our source code is available at


Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) is a promising and very ch...

Dual Cluster Contrastive learning for Person Re-Identification

Recently, cluster contrastive learning has been proven effective for per...

Implicit Sample Extension for Unsupervised Person Re-Identification

Most existing unsupervised person re-identification (Re-ID) methods use ...

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

The unsupervised domain adaptive person re-identification (re-ID) task h...

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

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

FlipReID: Closing the Gap between Training and Inference in Person Re-Identification

Since neural networks are data-hungry, incorporating data augmentation i...

Unsupervised Person Re-identification with Stochastic Training Strategy

Unsupervised person re-identification (re-ID) has attracted increasing r...