HyperAI

Unsupervised Domain Adaptation On Market To

Métriques

mAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
mAP
Paper TitleRepository
EvoADA71.4On Evolving Attention Towards Domain Adaptation-
TJ-AIDL23.0Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification-
PCB-PAST54.3Self-training with progressive augmentation for unsupervised cross-domain person re-identification
SDA61.4Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
CFSM27.3Disjoint Label Space Transfer Learning with Common Factorised Space-
SPGAN22.3Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
CCTSE72.6Unsupervised and self-adaptative techniques for cross-domain person re-identification
UCDA31.0A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification-
ENC40.4Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
SNR58.1Style Normalization and Restitution for Generalizable Person Re-identification
OG-Net13.7Parameter-Efficient Person Re-identification in the 3D Space
PDA-Net45.1Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation-
ECN++54.4Learning to Adapt Invariance in Memory for Person Re-identification-
MMCL51.4Unsupervised Person Re-identification via Multi-label Classification-
CORE-ReID74.8CORE-ReID: Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-Identification
SSG53.4Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
AWB71.0Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
SpCL68.8Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
ACT54.5Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
MMT65.1Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
0 of 25 row(s) selected.