Progressive Cluster Purification for Unsupervised Feature Learning

07/06/2020
by   Yifei Zhang, et al.
7

In unsupervised feature learning, sample specificity based methods ignore the inter-class information, which deteriorates the discriminative capability of representation models. Clustering based methods are error-prone to explore the complete class boundary information due to the inevitable class inconsistent samples in each cluster. In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner. Our approach, referred to as Progressive Cluster Purification (PCP), implements progressive clustering by gradually reducing the number of clusters during training, while the sizes of clusters continuously expand consistently with the growth of model representation capability. With a well-designed cluster purification mechanism, it further purifies clusters by filtering noise samples which facilitate the subsequent feature learning by utilizing the refined clusters as pseudo-labels. Experiments demonstrate that the proposed PCP improves baseline method with significant margins. Our code will be available at https://github.com/zhangyifei0115/PCP.

READ FULL TEXT
research
04/14/2022

Implicit Sample Extension for Unsupervised Person Re-Identification

Most existing unsupervised person re-identification (Re-ID) methods use ...
research
06/10/2019

Progressive Cluster Purification for Transductive Few-shot Learning

Few-shot learning aims to learn to generalize a classifier to novel clas...
research
06/18/2020

Online Deep Clustering for Unsupervised Representation Learning

Joint clustering and feature learning methods have shown remarkable perf...
research
08/07/2021

Towards Discriminative Representation Learning for Unsupervised Person Re-identification

In this work, we address the problem of unsupervised domain adaptation f...
research
12/09/2021

Dual Cluster Contrastive learning for Person Re-Identification

Recently, cluster contrastive learning has been proven effective for per...
research
01/23/2023

Triplet Contrastive Learning for Unsupervised Vehicle Re-identification

Part feature learning is a critical technology for finegrained semantic ...
research
03/27/2022

DeepDPM: Deep Clustering With an Unknown Number of Clusters

Deep Learning (DL) has shown great promise in the unsupervised task of c...

Please sign up or login with your details

Forgot password? Click here to reset