Group-aware Label Transfer for Domain Adaptive Person Re-identification

  title={Group-aware Label Transfer for Domain Adaptive Person Re-identification},
  author={Kecheng Zheng and Wu Liu and Lingxiao He and Tao Mei and Jiebo Luo and Zhengjun Zha},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Kecheng ZhengWu Liu Zhengjun Zha
  • Published 23 March 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine clustering-based pseudo-label prediction with representation learning and perform the two steps in an alternating fashion. However, offline interaction between these two steps may allow noisy pseudo labels to substantially hinder the capability of the model… 

Figures and Tables from this paper

Refining Pseudo Labels for Unsupervised Domain Adaptive Person Re-Identification

A novel framework to refine pseudo labels for UDA person re-identification with a No-Reference Light Enhancement network (NRLE-Net) and a novel feature extraction model called Trans-Encoder, designed based on Transformer.

Unsupervised confident co-promoting: refinery for pseudo labels on unsupervised person re-identification

This paper introduces a confidence strategy that greatly improves the confidence of generating pseudo labels in the case of multi-network collaboratively guided learning and achieves a significant improvement in common evaluation indicators in the four most common re-ID experiments compared to the state-of-the-art (SOTA) methods.

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

This paper presents a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster and proposes Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples.

Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification

A novel hierarchical clustering scheme is proposed to promote clustering quality, and an uncertainty-aware collaborative instance selection method is introduced to select images with reliable labels for model training that effectively reduces the impact of noisy labels.

Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification

An approach named probabilistic uncertainty guided progressive label refinery (P2LR) for domain adaptive person re-identification to model the labeling uncertainty with the Probabilistic distance along with ideal single-peak distributions and explores a progressive strategy for refining pseudo labels.

Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework

This work proposes a simple and efficient domain-specific adaptive framework, and realizes it with an adaptive normalization module designed upon the batch and instance normalization techniques, which successfully yield reliable pseudo-labels to implement training and also enhance the domain generalization capability of the model as required.

Global Relation-Aware Contrast Learning for Unsupervised Person Re-Identification

A Global Relation-Aware Contrast Learning (GRACL) method for the task of unsupervised Re-ID that designs both inter- and intra-ID relation-aware contrastive learning modules to facilitate model learning.

Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification

The plug-and-play g raph-based pseudo l abel c orrection network (GLC) is proposed to refine the pseudo labels in the manner of supervised clustering to improve the quality of pseudo labels though the supervision signals contain some noise, leading to better Re-ID performance.

Complementary Attention-Driven Contrastive Learning With Hard-Sample Exploring for Unsupervised Domain Adaptive Person Re-ID

A complementary attention-driven contrastive learning with hard-sample exploring (CACHE) algorithm, which significantly outperforms state-of-the-art methods in terms of mAP and CMC.

Reliability Exploration with Self-Ensemble Learning for Domain Adaptive Person Re-identification

This paper proposes a Reliability Exploration with Self-ensemble Learning (RESL) framework for domain adaptive person ReID and demonstrates that this method can signifcantly surpass the state-of-the-art performance on the unsupervised domain adaptive people ReID.



Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

This work proposes a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID.

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.

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.

Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification

This work introduces an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identity-discriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain.

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.

A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification

The experimental results demonstrate that the bottom-up clustering approach to jointly optimize a convolutional neural network and the relationship among the individual samples is not only superior to state-of-the-art unsupervised re-ID approaches, but also performs favorably than competing transfer learning and semi-supervised learning methods.

Unsupervised Person Re-Identification by Soft Multilabel Learning

The reference agent learning to represent each reference person by a reference agent in a joint embedding is introduced and the unified deep model outperforms the state-of-the-art unsupervised RE-ID methods by clear margins.

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

A novel category anchor-guided (CAG) UDA model for semantic segmentation is proposed, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously.

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.

Unsupervised Domain Adaptive Re-Identification: Theory and Practice