• Corpus ID: 232352862

Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification

  title={Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification},
  author={Zhizheng Zhang and Cuiling Lan and Wenjun Zeng and Quanzeng You and Zicheng Liu and Kecheng Zheng and Zhibo Chen},
Unsupervised domain adaptive (UDA) person reidentification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. To address this problem, we propose a Disentanglement-based Cross-Domain Feature Augmentation (DCDFA) strategy, where the augmented features characterize well the target and source domain data distributions while inheriting… 

Figures and Tables from this paper

Calibrated Feature Decomposition for Generalizable Person Re-Identification

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.



Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification

A novel unsupervised domain adaption framework which transfers discriminative representations from the labeled source domain to the unlabeled target domain (dataset) and a novel domain similarity loss is proposed based on one-class classification.

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

The proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep image representation with pose and domain information properly disentangled and is able to perform pose disentangling across domains without supervision in identities, and the resulting features can be applied to cross-dataset re-ID.

AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification

A novel augmented discriminative clustering (AD-Cluster) technique that estimates and augments person clusters in target domains and enforces the discrimination ability of re-ID models with the augmented clusters.

Domain Adaptive Person Re-Identification via Coupling Optimization

A coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization (GLO), respectively, designed to train the ReID model with unsupervised setting on the target domain.

Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification

A self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset and introduces a ranking-based triplet loss in the conservative stage, which is a label-free objective function based on the similarities between data pairs.

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification

Results on three re-ID domains show that the domain adaptation accuracy outperforms the state of the art by a large margin and the three invariance properties and the proposed memory are indispensable towards an effective domain adaptation system.

Structured Domain Adaptation for Unsupervised Person Re-identification

An end-to-end structured domain adaptation framework that consists of a novel structured domain-translation network and two domain-specific person image encoders that outperforms state-of-the-art methods on multiple UDA tasks of re-identification.

Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification

An asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other, which can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy.

Adaptive Transfer Network for Cross-Domain Person Re-Identification

A novel adaptive transfer network (ATNet) for effective cross-domain person re-identification that decomposes the complicated cross- domain transfer into a set of factor-wise sub-transfers and gives ATNet the capability of precise style transfer at factor level and eventually effective transfer across domains.

Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification

A Self-similarity Grouping (SSG) approach, which exploits the potential similarity of unlabeled samples to build multiple clusters from different views automatically, and introduces a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting.