Camera-aware Proxies for Unsupervised Person Re-Identification
- URL: http://arxiv.org/abs/2012.10674v2
- Date: Fri, 5 Feb 2021 12:41:42 GMT
- Title: Camera-aware Proxies for Unsupervised Person Re-Identification
- Authors: Menglin Wang, Baisheng Lai, Jianqiang Huang, Xiaojin Gong, Xian-Sheng
Hua
- Abstract summary: This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations.
We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera.
Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
- Score: 60.26031011794513
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper tackles the purely unsupervised person re-identification (Re-ID)
problem that requires no annotations. Some previous methods adopt clustering
techniques to generate pseudo labels and use the produced labels to train Re-ID
models progressively. These methods are relatively simple but effective.
However, most clustering-based methods take each cluster as a pseudo identity
class, neglecting the large intra-ID variance caused mainly by the change of
camera views. To address this issue, we propose to split each single cluster
into multiple proxies and each proxy represents the instances coming from the
same camera. These camera-aware proxies enable us to deal with large intra-ID
variance and generate more reliable pseudo labels for learning. Based on the
camera-aware proxies, we design both intra- and inter-camera contrastive
learning components for our Re-ID model to effectively learn the ID
discrimination ability within and across cameras. Meanwhile, a proxy-balanced
sampling strategy is also designed, which facilitates our learning further.
Extensive experiments on three large-scale Re-ID datasets show that our
proposed approach outperforms most unsupervised methods by a significant
margin. Especially, on the challenging MSMT17 dataset, we gain $14.3\%$ Rank-1
and $10.2\%$ mAP improvements when compared to the second place. Code is
available at: \texttt{https://github.com/Terminator8758/CAP-master}.
Related papers
- Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities.
Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
arXiv Detail & Related papers (2024-06-10T06:26:03Z) - Pseudo Labels Refinement with Intra-camera Similarity for Unsupervised
Person Re-identification [8.779246907359706]
Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels.
Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise caused by domain shifts among different cameras.
We propose a novel label refinement framework with clustering intra-camera similarity.
arXiv Detail & Related papers (2023-04-25T08:04:12Z) - 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) - Unsupervised Pretraining for Object Detection by Patch Reidentification [72.75287435882798]
Unsupervised representation learning achieves promising performances in pre-training representations for object detectors.
This work proposes a simple yet effective representation learning method for object detection, named patch re-identification (Re-ID)
Our method significantly outperforms its counterparts on COCO in all settings, such as different training iterations and data percentages.
arXiv Detail & Related papers (2021-03-08T15:13:59Z) - Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for
Unsupervised Person Re-Identification [60.36551512902312]
unsupervised person re-identification (re-ID) aims to learn discriminative models with unlabeled data.
One popular method is to obtain pseudo-label by clustering and use them to optimize the model.
In this paper, we propose a unified framework to solve both problems.
arXiv Detail & Related papers (2021-03-08T09:13:06Z) - Learn by Guessing: Multi-Step Pseudo-Label Refinement for Person
Re-Identification [0.0]
A promising approach relies on the use of unsupervised learning as part of the pipeline.
In this work, we propose a multi-step pseudo-label refinement method to select the best possible clusters.
We surpass state-of-the-art for UDA Re-ID by 3.4% on Market1501-DukeMTMC datasets.
arXiv Detail & Related papers (2021-01-04T20:00:33Z) - 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) - Intra-Camera Supervised Person Re-Identification [87.88852321309433]
We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation.
This eliminates the most time-consuming and tedious inter-camera identity labelling process.
We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
arXiv Detail & Related papers (2020-02-12T15:26:33Z)
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.