Calibrated Feature Decomposition for Generalizable Person Re-Identification

by   Kecheng Zheng, et al.

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 calibrated-and-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 id-relevant 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:


page 2

page 5

page 6

page 7

page 8

page 9

page 10

page 12


Style Normalization and Restitution for Generalizable Person Re-identification

Existing fully-supervised person re-identification (ReID) methods usuall...

Domain generalization Person Re-identification on Attention-aware multi-operation strategery

Domain generalization person re-identification (DG Re-ID) aims to direct...

NFormer: Robust Person Re-identification with Neighbor Transformer

Person re-identification aims to retrieve persons in highly varying sett...

Style Variable and Irrelevant Learning for Generalizable Person Re-identification

Recently, due to the poor performance of supervised person re-identifica...

Deep Multimodal Fusion for Generalizable Person Re-identification

Person re-identification plays a significant role in realistic scenarios...

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

Although supervised person re-identification (Re-ID) methods have shown ...

Hazy Re-ID: An Interference Suppression Model For Domain Adaptation Person Re-identification Under Inclement Weather Condition

In a conventional domain adaptation person Re-identification (Re-ID) tas...

Please sign up or login with your details

Forgot password? Click here to reset