Unsupervised Domain Adaptation On Market To

評価指標

mAP

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	mAP	Paper Title	Repository
EvoADA	71.4	On Evolving Attention Towards Domain Adaptation	-
TJ-AIDL	23.0	Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification	-
PCB-PAST	54.3	Self-training with progressive augmentation for unsupervised cross-domain person re-identification
SDA	61.4	Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
CFSM	27.3	Disjoint Label Space Transfer Learning with Common Factorised Space	-
SPGAN	22.3	Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
CCTSE	72.6	Unsupervised and self-adaptative techniques for cross-domain person re-identification
UCDA	31.0	A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification	-
ENC	40.4	Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
SNR	58.1	Style Normalization and Restitution for Generalizable Person Re-identification
OG-Net	13.7	Parameter-Efficient Person Re-identification in the 3D Space
PDA-Net	45.1	Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation	-
ECN++	54.4	Learning to Adapt Invariance in Memory for Person Re-identification	-
MMCL	51.4	Unsupervised Person Re-identification via Multi-label Classification	-
CORE-ReID	74.8	CORE-ReID: Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-Identification
SSG	53.4	Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
AWB	71.0	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
SpCL	68.8	Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
ACT	54.5	Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
MMT	65.1	Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

0 of 25 row(s) selected.