Unsupervised Person Re-Identification

26 papers with code • 8 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

Latest papers without code

Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification

15 Jun 2021

To be specific, we propose a novel cluster-level contrastive loss to help the siamese network effectively mine the invariance in feature learning with respect to the cluster structure within and between different data augmentation views, respectively.

Clustering Data Augmentation +1

Large-Scale Unsupervised Person Re-Identification with Contrastive Learning

17 May 2021

In particular, most existing unsupervised and domain adaptation ReID methods utilize only the public datasets in their experiments, with labels removed.

Domain Adaptation Pedestrian Detection +2

Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning

1 Apr 2021

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models.

Clustering Unsupervised Person Re-Identification

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

8 Mar 2021

The multi-label learning module leverages a memory feature bank and assigns each image with a multi-label vector based on the similarities between the image and feature bank.

Clustering Multi-Label Learning +1

Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification

12 Jan 2021

By studying two unsupervised person re-ID methods in a cross-method way, we point out a hard negative problem is handled implicitly by their designs of data augmentations and PK sampler respectively.

Unsupervised Person Re-Identification

Fully Unsupervised Person Re-identification viaSelective Contrastive Learning

15 Oct 2020

In this work, we propose a novel selective contrastive learning framework for unsupervised feature learning.

Representation Learning Unsupervised Person Re-Identification

Global Distance-distributions Separation for Unsupervised Person Re-identification

ECCV 2020

To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.

Domain Adaptation Unsupervised Person Re-Identification

Spatial-Aware GAN for Unsupervised Person Re-identification

26 Nov 2019

The recent person re-identification research has achieved great success by learning from a large number of labeled person images.

Unsupervised Domain Adaptation Unsupervised Person Re-Identification