Cluster Contrast for Unsupervised Person Re-Identification

• URL: http://arxiv.org/abs/2103.11568v1
• Date: Mon, 22 Mar 2021 03:41:19 GMT
• Title: Cluster Contrast for Unsupervised Person Re-Identification
• Authors: Zuozhuo Dai, Guangyuan Wang, Siyu Zhu, Weihao Yuan, Ping Tan
• Abstract summary: State-of-the-art unsupervised re-ID methods train neural networks using a memory-based non-improvementsoftmax loss. Duringtraining, the instance feature vectors are updated. How-ever, due to the varying cluster size, the updating progressfor each cluster is inconsistent. We present Cluster Contrast which stores feature vectors and computes contrast loss in the cluster level.
• Score: 38.6826925096453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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%, 7.5%, 6.6% compared to state-of-the-art purely unsupervised re-ID methods and 5.1%, 4.0%,6.5% mAP compared to the state-of-the-art unsuperviseddomain adaptation re-ID methods on the Market, Duke, andMSMT17 datasets.Our source code is available at https://github.com/wangguangyuan/ClusterContrast.git.

Related papers

• Reinforcement Graph Clustering with Unknown Cluster Number [91.4861135742095]
  We propose a new deep graph clustering method termed Reinforcement Graph Clustering. In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters.
  arXiv  Detail & Related papers  (2023-08-13T18:12:28Z)
• Implicit Sample Extension for Unsupervised Person Re-Identification [97.46045935897608]
  Clustering sometimes mixes different true identities together or splits the same identity into two or more sub clusters. We propose an Implicit Sample Extension (OurWholeMethod) method to generate what we call support samples around the cluster boundaries. Experiments demonstrate that the proposed method is effective and achieves state-of-the-art performance for unsupervised person Re-ID.
  arXiv  Detail & Related papers  (2022-04-14T11:41:48Z)
• Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification [31.065557919305892]
  Unsupervised person re-identification (Re-ID) has received increasing research attention. Most clustering-based methods take each cluster as a pseudo identity class. We propose to split each single cluster into multiple proxies according to camera views.
  arXiv  Detail & Related papers  (2022-01-15T10:12:03Z)
• Dual Cluster Contrastive learning for Person Re-Identification [78.42770787790532]
  We formulate a unified cluster contrastive framework, named Dual Cluster Contrastive learning (DCC) DCC maintains two types of memory banks: individual and centroid cluster memory banks. It can be easily applied for unsupervised or supervised person ReID.
  arXiv  Detail & Related papers  (2021-12-09T02:43:25Z)
• Mind Your Clever Neighbours: Unsupervised Person Re-identification via Adaptive Clustering Relationship Modeling [19.532602887109668]
  Unsupervised person re-identification (Re-ID) attracts increasing attention due to its potential to resolve the scalability problem of supervised Re-ID models. Most existing unsupervised methods adopt an iterative clustering mechanism, where the network was trained based on pseudo labels generated by unsupervised clustering. To generate high-quality pseudo-labels and mitigate the impact of clustering errors, we propose a novel clustering relationship modeling framework for unsupervised person Re-ID.
  arXiv  Detail & Related papers  (2021-12-03T10:55:07Z)
• Meta Clustering Learning for Large-scale Unsupervised Person Re-identification [124.54749810371986]
  We propose a "small data for big task" paradigm dubbed Meta Clustering Learning (MCL) MCL only pseudo-labels a subset of the entire unlabeled data via clustering to save computing for the first-phase training. Our method significantly saves computational cost while achieving a comparable or even better performance compared to prior works.
  arXiv  Detail & Related papers  (2021-11-19T04:10:18Z)
• Unsupervised Person Re-identification with Stochastic Training Strategy [29.639040901941726]
  State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy. Forcing images to get closer to the centroid emphasizes the result of clustering. Previous methods utilize features obtained at different training iterations to represent one centroid. We propose an unsupervised re-ID approach with a learning strategy.
  arXiv  Detail & Related papers  (2021-08-16T07:23:58Z)
• Unsupervised Person Re-identification via Softened Similarity Learning [122.70472387837542]
  Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-07T17:16:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.