Mar 22, 2021 · We present Cluster Contrast which stores feature vectors and computes contrast loss at the cluster level.

Unlike SwAV in which the number of clusters is fixed, the proposed Cluster. Contrast gradually selects reliable labels and dynamically refines the clustering.

Nov 19, 2021 · The official repository for Cluster Contrast for Unsupervised Person Re-Identification. We achieve state-of-the-art performances on unsupervised learning tasks ...

Feb 26, 2023 · We present Cluster Contrast which stores feature vectors and computes contrastive loss at the cluster level.

The Cluster Contrast is simple and effective. It can be used together with ex- isting unsupervised re-ID methods to further improve their performances. In.

State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to ...

Cluster Contrast employs a unique cluster representation to describe each cluster, resulting in a cluster-level memory dictionary, which can solve the ...

from setuptools import setup, find_packages setup(name='ClusterContrast', version='1.0.0', description='Cluster Contrast for Unsupervised Person ...

We propose a Federated Unsupervised Cluster-Contrastive (FedUCC) method based on deep learning for Person ReID that follows a generic-to-specific learning ...

Jan 27, 2023 · At each iteration, we follow the time contrast principle to select one camera centroid as proxy of each cluster. By enforcing the samples to ...