Group-aware Label Transfer for Domain Adaptive Person Re-identification

Zheng, Kecheng; Liu, Wu; He, Lingxiao; Mei, Tao; Luo, Jiebo; Zha, Zheng-Jun

doi:10.1109/cvpr46437.2021.00527

Cited by 171 publications

(42 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, our PDL only one encoder used is compared with the MMT [14] method that uses the two-stream network, showing a noticeable 6.4% and 14.9% improvements in terms of mAP on Market-to-Duke and Duke-to-Market respectively. Compared to the state-ofthe-art method GLT [41] which is based on label transfer, our method leads to 2.3% mAP and 4.4% mAP gain on Marketto-Duke and Duke-to-Market respectively. The results verify the effectiveness of our method.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 91%

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

Hou¹

2022

Preprint

View full text Add to dashboard Cite

The unsupervised domain adaptive person reidentification (re-ID) task has been a challenge because, unlike the general domain adaptive tasks, there is no overlap between the classes of source and target domain data in the person re-ID, which leads to a significant domain gap. State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based contrastive loss. However, performing contrastive learning by treating each unlabeled instance as a class will lead to the problem of class collision, and the updating intensity is inconsistent due to the difference in the number of instances of different categories when updating in the memory bank.To address such problems, we propose Prototype Dictionary Learning for person re-ID which is able to utilize both source domain data and target domain data by one training stage while avoiding the problem of class collision and the problem of updating intensity inconsistency by cluster-level prototype dictionary learning. In order to reduce the interference of domain gap on the model, we propose a local-enhance module to improve the domain adaptation of the model without increasing the number of model parameters. Our experiments on two large datasets demonstrate the effectiveness of the prototype dictionary learning. 71.5% mAP is achieved in the Market-to-Duke task, which is a 2.3% improvement compared to the state-of-theart unsupervised domain adaptive re-ID methods. It achieves 83.9% mAP in the Duke-to-Market task, which improves by 4.4% compared to the state-of-the-art unsupervised adaptive re-ID methods.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 91%

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

Hou¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Thirdly, DCC has better generalization capabilities, e.g., DCC achieves the better performance for both supervised and unsupervised person ReID on two datasets. SSG [16] 58.3 80.0 90.0 92.4 UGA [42] 70.3 87.2 --NRMT [48] 71.7 87.8 94.6 96.5 JVTC+ [4] 75.4 90.5 96.2 97.1 MMT [17] 75.6 89.3 95.8 97.5 SPCL [18] 77.5 89.7 96.1 97.6 ICE [3] 79.2 92.0 97.0 98.1 GLT [54] 79.5 92.2 96.5 97.8 FastReID [20] 80.5 92.7 --CACAL [30] 80.9 92.7 97.4 98.5 CC(ResNet50) [13] 82.6 93.0 97.0 98.1 CC(ResNet50-ibn) [13] 84…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…For example, Liu et al [32] use three GAN models to reduce the discrepancy between different domains in illumination, resolution, and camera-view, respectively. To handle the lack of annotation, many methods have been proposed to acquire reliable pseudo labels [15,31,46,47,54]. For example, Lin et al [31] propose a bottom-up unsupervised clustering method that simultaneously considers both diversity and similarity.…”

Section: Unsupervised Person Re-identificationmentioning

confidence: 99%

Dual Cluster Contrastive learning for Object Re-Identification

Yao¹,

Xu²

2021

Preprint

View full text Add to dashboard Cite

Recently, cluster contrastive learning has been proven effective for person ReID by computing the contrastive loss between the individual feature and the cluster memory. However, existing methods that use the individual feature to momentum update the cluster memory are not robust to the noisy samples, such as the samples with wrong annotated labels or the pseudo-labels. Unlike the individual-based updating mechanism, the centroid-based updating mechanism that applies the mean feature of each cluster to update the cluster memory is robust against minority noisy samples. Therefore, we formulate the individual-based updating and centroid-based updating mechanisms in a unified cluster contrastive framework, named Dual Cluster Contrastive learning (DCC), which maintains two types of memory banks: individual and centroid cluster memory banks. Significantly, the individual cluster memory is momentum updated based on the individual feature. The centroid cluster memory applies the mean feature of each cluter to update the corresponding cluster memory. Besides the vallina contrastive loss for each memory, a consistency constraint is applied to guarantee the consistency of the output of two memories. Note that DCC can be easily applied for unsupervised or supervised person ReID by using ground-truth labels or pseudo-labels generated with clustering method, respectively. Extensive experiments on two benchmarks under supervised person ReID and unsupervised person ReID demonstrate the superior of the proposed DCC. Code

show abstract

“…A memory based generalization loss and a meta batch normalization layer was also added to diversify the advantages of meta-learning. In [257] a Group-aware label transfer algorithm was proposed. It promotes the pseudo-labels via online interaction.…”

Section: Cnn-based Approachesmentioning

confidence: 99%

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Zahra¹,

Perwaiz²,

Shahzad³

et al. 2022

Preprint

View full text Add to dashboard Cite

Person re-identification (Re-ID) is one of the primary components of an automated visual surveillance system. It aims to automatically identify/search persons in a multi-camera network having non-overlapping field-of-views. Owing to its potential in various applications and research significance, a plethora of deep learning based re-Id approaches have been proposed in the recent years. However, there exist several vision related challenges, e.g., occlusion, pose scale & viewpoint variance, background clutter, person misalignment and cross-domain generalization across camera modalities, which makes the problem of re-Id still far from being solved. Majority of the proposed approaches directly or indirectly aim to solve one or multiple of these existing challenges. In this context, a comprehensive review of current re-ID approaches in solving theses challenges is needed to analyze and focus on particular aspects for further advancements. At present, such a focused review does not exist and henceforth in this paper, we have presented a systematic challenge-specific literature survey of 230+ papers between the years of 2015-21. For the first time a survey of this type have been presented where the person re-Id approaches are reviewed in such solution-oriented perspective. Moreover, we have presented several diversified prominent developing trends in the respective research domain which will provide a visionary perspective regarding ongoing person re-Id research and eventually help to develop practical real world solutions. Scope/Objective of the ReviewIn this paper, we have targeted the most popular challenges in person re-id to perform systematic challenge-wise review of the published approaches. In this context, we have collected papers from top conferences and journals for the years from 2015 to 2021. The progress in papers addressing each challenge and its influence on published results is

show abstract

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Cited by 171 publications

References 32 publications

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning

Dual Cluster Contrastive learning for Object Re-Identification

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Contact Info

Product

Resources

About