Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification

Han, Kuang-Wei; Huang, Yan; Chen, Zerui; Wang, Liang; Tan, Tieniu

doi:10.1007/978-3-030-58574-7_12

Cited by 24 publications

(30 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• When only ID loss is included, compared with Table I, it can be obviously found that the performance of our method surpasses almost all existing methods except INTACT [40] and PCB+PRI [62] on the Rank-1, and even reaches the same performance level of single PRI [62]. The results reflect the great feature extraction ability of HRNet on crossresolution person images which should be owed to its unique high-resolution parallel structure.…”

Section: E Ablation Studymentioning

confidence: 67%

“…We compare our PS-HRNet with a series of far-ranging state-of-the-art person re-ID methods, which can be roughly separated into two main categories. (1) Conventional methods designed for traditional person re-ID task: PCB [51], DenseNet-121 [52], ResNet-50 [53], SE-ResNet-50 [54], SPreID [28], Part Aligned [55], CamStyle [56] and FD-GAN [58]; (2) Pointed methods designed for cross-resolution person re-ID task: JUDEA [14], SDF [59], SLD 2 L [13], SING [16], CSR-GAN [38], FFSR [60], RIFE [60], FFSR+RIFE [60], RAIN [15], CAD-Net [39], CAD-Net++ [61], PRI [62], PCB+PRI [62] and PyrNet+PRI [62]. These methods in the comparison almost cover all the current methods in the crossresolution re-ID field.…”

Section: Comparisons To State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Guo-qing¹,

Yu²,

Dong³

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. In practical applications, due to the differences in camera performance and distance between cameras and persons of interest, captured person images usually have various resolutions. We name this problem as Cross-Resolution Person Re-identification which brings a great challenge for matching correctly. In this paper, we propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the above problem. Specifically, in order to restore the resolution of low-resolution images and make reasonable use of different channel information of feature maps, we introduce and innovate VDSR module with channel attention (CA) mechanism, named as VDSR-CA. Then we reform the HRNet by designing a novel representation head to extract discriminating features, named as HRNet-ReID. In addition, a pseudo-siamese framework is constructed to reduce the difference of feature distributions between low-resolution images and high-resolution images. The experimental results on five cross-resolution person datasets verify the effectiveness of our proposed approach. Compared with the state-of-the-art methods, our proposed PS-HRNet improves 3.4%, 6.2%, 2.5%,1.1% and 4.2% at Rank-1 on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively. Our code is available at https://github.com/zhguoqing.

show abstract

Section: E Ablation Studymentioning

confidence: 67%

Section: Comparisons To State-of-the-art Methodsmentioning

confidence: 99%

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Guo-qing¹,

Yu²,

Dong³

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The FSL head G aims to learn discriminative identity features from the source labeled data for re-id. Many re-id models containing BN layers (Han et al 2020; Wang 2020) can be adopted as the backbone of our feature extractor E. Here we choose DualNorm (Jia, Ruan, and Hospedales 2019) for its competitive generalization ability and relatively concise structure. For a given input image x i ∈ D, we denote the extracted feature maps as E(x i ) ∈ R C×H×W , where C is the number of channels, H and W are the height and width, respectively.…”

Section: Fsl: Global Identity Learningmentioning

confidence: 99%

Generalizable Person Re-identification via Self-Supervised Batch Norm Test-Time Adaption

Han

Huang

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important tool of regularizing the distribution, batch normalization (BN) has been widely used in existing methods. However, they neglect that BN is severely biased to the training domain and inevitably suffers the performance drop if directly generalized without being updated. To tackle this issue, we propose Batch Norm Test-time Adaption (BNTA), a novel re-id framework that applies the self-supervised strategy to update BN parameters adaptively. Specifically, BNTA quickly explores the domain-aware information within unlabeled target data before inference, and accordingly modulates the feature distribution normalized by BN to adapt to the target domain. This is accomplished by two designed self-supervised auxiliary tasks, namely part positioning and part nearest neighbor matching, which help the model mine the domain-aware information with respect to the structure and identity of body parts, respectively. To demonstrate the effectiveness of our method, we conduct extensive experiments on three re-id datasets and confirm the superior performance to the state-of-the-art methods.

show abstract

“…In the presented procedure pair of high resolution and low resolution dictionaries and mappings functions are learned during training, due to this learned dictionary and mapping function low resolution images would be converted to high resolution discriminant features. Ke Han et al in [210] challenged the issue of low resolution. Presented model predicts and recovers the content aware details.…”

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

Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification

Cited by 24 publications

References 39 publications

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Generalizable Person Re-identification via Self-Supervised Batch Norm Test-Time Adaption

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

Contact Info

Product

Resources

About