Unsupervised Domain Adaptation On Duke To 1

Métriques

mAP

rank-1

rank-10

rank-5

Résultats

Résultats de performance de divers modèles sur ce benchmark

					Paper Title
CORE-ReID	45.2	72.2	86.3	82.9	CORE-ReID: Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-Identification
CCTSE	34.5	63.9	79.6	75.3	Unsupervised and self-adaptative techniques for cross-domain person re-identification
AWB	30.7	62.7	79.0	74.5	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
SpCL	26.5	53.1	70.5	65.8	Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
SDA	25.6	54.4	71.3	66.4	Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
MMT	23.3	50.1	69.8	63.9	Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
MMCL	16.2	43.6	58.9	54.3	Unsupervised Person Re-identification via Multi-label Classification
ECN++	16.0	42.5	61.5	55.9	Learning to Adapt Invariance in Memory for Person Re-identification
SSG	13.3	32.2	51.2	-	Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
ECN	10.2	30.2	46.8	41.5	Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
DG-Net	6.35	20.59	37.04	31.67	Joint Discriminative and Generative Learning for Person Re-identification
PTGAN	3.3	11.8	27.4	-	Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
OG-Net	1.9	6.8	-	-	Parameter-Efficient Person Re-identification in the 3D Space

0 of 13 row(s) selected.

Unsupervised Domain Adaptation On Duke To 1 | SOTA | HyperAI