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

by   Guodong Ding, et al.

Person re-identification aims to establish the correct identity correspondences of a person moving through a non-overlapping multi-camera installation. Recent advances based on deep learning models for this task mainly focus on supervised learning scenarios where accurate annotations are assumed to be available for each setup. Annotating large scale datasets for person re-identification is demanding and burdensome, which renders the deployment of such supervised approaches to real-world applications infeasible. Therefore, it is necessary to train models without explicit supervision in an autonomous manner. In this paper, we propose an elegant and practical clustering approach for unsupervised person re-identification based on the cluster validity consideration. Concretely, we explore a fundamental concept in statistics, namely dispersion, to achieve a robust clustering criterion. Dispersion reflects the compactness of a cluster when employed at the intra-cluster level and reveals the separation when measured at the inter-cluster level. With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data. This approach considers a wider context of sample-level pairwise relationships to achieve a robust cluster affinity assessment which handles the complications may arise due to prevalent imbalanced data distributions. Additionally, our solution can automatically prioritize standalone data points and prevents inferior clustering. Our extensive experimental analysis on image and video re-identification benchmarks demonstrate that our method outperforms the state-of-the-art unsupervised methods by a significant margin. Code is available at


page 1

page 6

page 8


Energy Clustering for Unsupervised Person Re-identification

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

Cluster Contrast for Unsupervised Person Re-Identification

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

Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

Recent advances in person re-identification have demonstrated enhanced d...

Scalable Person Re-identification on Supervised Smoothed Manifold

Most existing person re-identification algorithms either extract robust ...

Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification

Unsupervised person re-identification (ReID) aims at learning discrimina...

Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) aims to match a query image...

Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification

Recently, large-scale synthetic datasets are shown to be very useful for...

Please sign up or login with your details

Forgot password? Click here to reset