Unsupervised Person Re Identification On 4

Métriques

MAP

Rank-1

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	MAP	Rank-1	Paper Title	Repository
TransReID-SSL (ViTi-S)	89.6	95.3	Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
PCL-CLIP (O2CAP)	88.4	94.8	Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
TransReID-SSL (ViT-S)	88.2	94.2	Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Cluster Contrast	83	92.9	Cluster Contrast for Unsupervised Person Re-Identification
PUL	20.5	45.5	Unsupervised Person Re-identification: Clustering and Fine-tuning
TMGF	89.5	95.5	Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
CA-Jaccard	86.1	94.4	CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
MGCE-HCL	79.6	92.1	Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification	-
SpCL	72.6	87.7	Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
ECN	43	75.1	Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
TransReID-SSL (ViT-S w/o RK)	-	95.3	Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Group Sampling	79.2	92.3	Rethinking Sampling Strategies for Unsupervised Person Re-identification
PCL-CLIP (CC)	86.9	94.2	Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
PCL-CLIP (CAP)	87.4	93.9	Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
ICE	82.3	93.8	ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
SPGAN+LMP	26.7	57.7	Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Self-Similarity Grouping (one shot)	71.5	87.5	Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
Dispersion based Clustering	41.3	69.2	Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification
PPLR	84.4	94.3	Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
CACL	80.9	92.7	Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification

0 of 23 row(s) selected.