Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Lin, Ci-Siang; Cheng, Yuan-Chia; Frank, Wang Yu-Chiang

doi:10.48550/arxiv.2010.09561

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing DG person Re-ID methods (Zhao et al 2021;Choi et al 2021;Song et al 2019;Lin, Li, and Kot 2020;Chen et al 2021;Jin et al 2020;Tamura and Murakami 2019) can be divided into two categories: single model methods and ensemble learning based methods. For the single model methods, Chen et al (Chen et al 2021) proposed a Dual Distribution Alignment Network with dual-level constraints, i.e., a domainwise adversarial feature learning and an identity-wise similarity enhancement, which maps pedestrian images into a domain-invariant feature space.…”

Section: Related Work Dg Person Re-identificationmentioning

confidence: 99%

“…Choi et al (Choi et al 2021) designed learnable batch-instance normalization layers, which prevents the model from overfitting to the source domains by the simulation of unsuccessful generalization scenarios in meta-learning pipeline. Lin et al (Lin, Cheng, and Wang 2020) present an episodic learning scheme, which advances meta-learning algorithm to exploit the labeled data from source domain and learns domaininvariant features without observing target domain data.…”

Section: Related Work Dg Person Re-identificationmentioning

confidence: 99%

See 1 more Smart Citation

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Liu

Huang

et al. 2022

AAAI

View full text Add to dashboard Cite

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

show abstract

Section: Related Work Dg Person Re-identificationmentioning

confidence: 99%

Section: Related Work Dg Person Re-identificationmentioning

confidence: 99%

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Liu

Huang

et al. 2022

AAAI

View full text Add to dashboard Cite

show abstract

Section: Dg Person Re-identificationmentioning

confidence: 99%

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

Liu¹,

Huang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person reidentification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

show abstract

“…Generalization capability to unseen domains is crucial for person re-id models when deploying to practical applications. To address this problem, several tailored DG-ReID methods [6,7,25,28,31,32,43,53] have been proposed, which can be mainly divided into three categories: metalearning based model, ensemble learning based model and disentanglement based model. Due to the success of disentangled learning, the DG-ReID methods based on disentangled learning [10,20,41,54] improve the model generalization ability by disentangling person representations into identity-irrelevant interference and id-invariant feature.…”

Section: Domain Generalizable Re-identificationmentioning

confidence: 99%

Calibrated Feature Decomposition for Generalizable Person Re-Identification

Zheng

Liu²,

Wu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Existing disentangled-based methods for generalizable person re-identification aim at directly disentangling person representations into domain-relevant interference and identity-relevant feature. However, they ignore that some crucial characteristics are stubbornly entwined in both the domain-relevant interference and identity-relevant feature, which are intractable to decompose in an unsupervised manner. In this paper, we propose a simple yet effective Calibrated Feature Decomposition (CFD) module that focuses on improving the generalization capacity for person re-identification through a more judicious feature decomposition and reinforcement strategy. Specifically, a calibratedand-standardized Batch normalization (CSBN) is designed to learn calibrated person representation by jointly exploring intra-domain calibration and inter-domain standardization of multi-source domain features. CSBN restricts instance-level inconsistency of feature distribution for each domain and captures intrinsic domain-level specific statistics. The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one. For enhancing the generalization ability and ensuring high discrimination of the identity-relevant feature, a calibrated instance normalization (CIN) is introduced to enforce discriminative idrelevant information, and filter out id-irrelevant information, and meanwhile the rich complementary clues from the remaining entangled feature are further employed to strengthen it. Extensive experiments demonstrate the strong generalization capability of our framework. Our models empowered by CFD modules significantly outperform the state-of-the-art domain generalization approaches on multiple widely-used benchmarks. Code will be made public: https://github.com/zkcys001/CFD.

show abstract

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Cited by 3 publications

References 0 publications

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-identification

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

Calibrated Feature Decomposition for Generalizable Person Re-Identification

Contact Info

Product

Resources

About