Unsupervised Domain Adaptation On Duke To

Métriques

mAP

rank-1

rank-10

rank-5

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mAP	rank-1	rank-10	rank-5	Paper Title	Repository
AD-Cluster	68.3	86.7	96.5	94.4	AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification	-
MMT	71.2	87.7	96.9	94.9	Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
TJ-AIDL	26.5	58.2	81.1	74.8	Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification	-
SPGAN	22.8	51.5	76.8	70.1	Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
SpCL	76.7	90.3	97.7	96.2	Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
ECN++	63.8	84.1	95.4	92.8	Learning to Adapt Invariance in Memory for Person Re-identification	-
CORE-ReID	84.4	93.6	98.7	97.7	CORE-ReID: Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-Identification
SNR	61.7	82.8	-	-	Style Normalization and Restitution for Generalizable Person Re-identification
UDAP	53.7	75.8	93.2	89.5	Unsupervised Domain Adaptive Re-Identification: Theory and Practice
CCTSE	78.4	92.9	97.8	96.9	Unsupervised and self-adaptative techniques for cross-domain person re-identification
EvoADA	84.3	-	-	-	On Evolving Attention Towards Domain Adaptation	-
CFSM	28.3	61.2	-	-	Disjoint Label Space Transfer Learning with Common Factorised Space	-
DG-Net	26.83	56.12	78.12	72.18	Joint Discriminative and Generative Learning for Person Re-identification
ARN	39.4	70.3	86.3	80.4	Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification	-
OGNet	14.7	36.4	-	-	Parameter-Efficient Person Re-identification in the 3D Space
LF2	83.2	92.8	-	-	Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
PCB-PAST	54.6	78.4	-	-	Self-training with progressive augmentation for unsupervised cross-domain person re-identification
ACT	60.6	80.5	-	-	Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
SDA	70.0	86.9	96.3	94.4	Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
CBN+ECN	52	81.7	94.7	91.9	Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

0 of 26 row(s) selected.