Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

Bai, Zechen; Wang, Zhigang; Wang, Jian; Hu, Di; Ding, Errui

doi:10.1109/cvpr46437.2021.01272

Cited by 66 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Unsupervised domain adaptation methods which assume a labelled source domain and an unlabelled target domain with different data distribution or image style. Recent works (Zheng et al 2021;Wu, Zheng, and Lai 2019;Zhao et al 2020b;Zhang et al 2021;Bai et al 2021) try to mitigate the domain gap between them for domain adaptation. (4) Pureunsupervised methods which suppose labelled source data is not available.…”

Section: Related Work Person Re-identificationmentioning

confidence: 99%

Lifelong Person Re-identification by Pseudo Task Knowledge Preservation

et al. 2022

AAAI

View full text Add to dashboard Cite

In real world, training data for person re-identification (Re-ID) is collected discretely with spatial and temporal variations, which requires a model to incrementally learn new knowledge without forgetting old knowledge. This problem is called lifelong person re-identification (LReID). Variations of illumination and background for images of each task exhibit task-specific image style and lead to task-wise domain gap. In addition to missing data from the old tasks, task-wise domain gap is a key factor for catastrophic forgetting in LReID, which is ignored in existing approaches for LReID. The model tends to learn task-specific knowledge with task-wise domain gap, which results in stability and plasticity dilemma. To overcome this problem, we cast LReID as a domain adaptation problem and propose a pseudo task knowledge preservation framework to alleviate the domain gap. Our framework is based on a pseudo task transformation module which maps the features of the new task into the feature space of the old tasks to complement the limited saved exemplars of the old tasks. With extra transformed features in the task-specific feature space, we propose a task-specific domain consistency loss to implicitly alleviate the task-wise domain gap for learning task-shared knowledge instead of task-specific one. Furthermore, to guide knowledge preservation with the feature distributions of the old tasks, we propose to preserve knowledge on extra pseudo tasks which jointly distills knowledge and discriminates identity, in order to achieve a better trade-off between stability and plasticity for lifelong learning with task-wise domain gap. Extensive experiments demonstrate the superiority of our method as compared with the state-of-the-art lifelong learning and LReID methods.

show abstract

Section: Related Work Person Re-identificationmentioning

confidence: 99%

Lifelong Person Re-identification by Pseudo Task Knowledge Preservation

et al. 2022

AAAI

View full text Add to dashboard Cite

show abstract

“…They have introduced novel dissimilarity based discrepancy loss that made the source and target distribution similar to make the results more efficient. Multi-source domain training to make the model generalize on multiple unseen domain was a way adopted in [251]. For this purpose, there comes a problem of domain gaps.…”

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

“…We compare LF 2 framework with state-of-the-art methods including: GAN transferring based methods (SPGAN+LMP [23], PDA-Net [24]), joint learning based methods (ECN [25], MMCL [27], JVTC+ [26], IDM [28]) and fine-tuning based methods (SSG [7], ADTC [9], AD-Cluster [8], MMT [10], MEB-Net [11], Dual-Refinement [15], UNRN [14], GLT [12], HCD [13], P 2 LR [32], RDSBN+MDIF [33]). The comparison results are shown in Table I.…”

Section: B Comparison With the State-of-the-artmentioning

confidence: 99%

“…Based on joint learning method, IDM [28] uses domain specific batch normalization and achieves best Rank-1 accuracy. RDSBN+MDIF [33] and P 2 LR [32] methods also construct teacher-student networks as baseline. However, these fine-tuning methods only focus on either pseudo labels refinery or domain-level information fusion.…”

Section: B Comparison With the State-of-the-artmentioning

confidence: 99%

Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification

Ding¹,

Zhou²

2022

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptive (UDA) person reidentification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding global features for pseudo labels generation, neglecting the local feature that can provide for the fine-grained information.To handle this issue, we propose a Learning Feature Fusion (LF 2 ) framework for adaptively learning to fuse global and local features to obtain a more comprehensive fusion feature representation. Specifically, we first pre-train our model within a source domain, then fine-tune the model on unlabeled target domain based on the teacher-student training strategy. The average weighting teacher network is designed to encode global features, while the student network updating at each iteration is responsible for fine-grained local features. By fusing these multiview features, multi-level clustering is adopted to generate diverse pseudo labels. In particular, a learnable Fusion Module (F M ) for giving prominence to fine-grained local information within the global feature is also proposed to avoid obscure learning of multiple pseudo labels. Experiments show that our proposed LF 2 framework outperforms the state-of-the-art with 73.5% mAP and 83.7% Rank1 on Market1501 to DukeMTMC-ReID, and achieves 83.2% mAP and 92.8% Rank1 on DukeMTMC-ReID to Market1501.

show abstract

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

Cited by 66 publications

References 26 publications

Lifelong Person Re-identification by Pseudo Task Knowledge Preservation

Lifelong Person Re-identification by Pseudo Task Knowledge Preservation

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

Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification

Contact Info

Product

Resources

About