Text-to-Image Person Re-identification on CUHK-PEDES (test)
79.98Rank-1 Accuracy (R-1)BAMG
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| BAMG2026.01 | 79.98 | 92.31 | 94.03 | — | — | — | |
| Our ICL*Training Sets=CUHK-PEDES2025.05 | 77.91 | 90.27 | 94.14 | 69.13 | 53.4 | — | |
| DiCo2026.01 | 77.21 | 91.85 | 95.63 | — | — | — | |
| RaSaImage Enc.=ALBEFF, Text Enc.=ALBEFF2023.08 | 76.51 | 90.29 | 94.25 | 69.38 | — | — | |
| Our ICLTraining Sets=CUHK-PEDES2025.05 | 76.41 | 90.48 | 94.33 | 68.04 | 51.99 | — | |
| ICL2026.01 | 76.41 | 90.48 | 94.33 | — | — | — | |
| RDETraining Sets=CUHK-PEDES2025.05 | 75.94 | 90.14 | 94.12 | 67.56 | 51.44 | — | |
| RDE2026.01 | 75.94 | 90.14 | 94.12 | — | — | — | |
| RDENoise Rate=0%, Checkpoint Selection=Best2023.08 | 75.94 | 90.14 | 94.12 | 67.56 | 51.44 | — | |
| Our RDEImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 75.94 | 90.14 | 94.12 | 67.56 | 51.44 | — | |
| CFAM2026.01 | 75.6 | 90.53 | 94.36 | — | — | — | |
| PLIPBackbone=Swin-B2023.05 | 75.36 | — | 94.87 | — | — | — | |
| PLOT2026.01 | 75.28 | 90.42 | 94.12 | — | — | — | |
| DCELImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 75.02 | 90.89 | 94.52 | — | — | — | |
| RDENoise Rate=20%, Checkpoint Selection=Last2023.08 | 74.53 | 89.23 | 93.55 | 66.13 | 49.63 | — | |
| RDENoise Rate=20%, Checkpoint Selection=Best2023.08 | 74.46 | 89.42 | 93.63 | 66.13 | 49.66 | — | |
| MUM2026.01 | 74.25 | 89.83 | 93.58 | — | — | — | |
| IRMmode=MTL, trained with multiple datasets=true2023.06 | 74.2 | — | — | 66.5 | — | — | |
| BiLMaImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 74.03 | 89.59 | 93.62 | 66.57 | — | — | |
| PLIPBackbone=RN1522023.05 | 73.68 | — | 94.22 | — | — | — | |
| TBPS2026.01 | 73.54 | 88.19 | 92.35 | — | — | — | |
| TBPSImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 73.54 | 88.19 | 92.35 | 65.38 | — | — | |
| IRRATraining Sets=CUHK-PEDES2025.05 | 73.38 | 89.93 | 93.71 | 66.13 | 50.24 | — | |
| IRRA2026.01 | 73.38 | 89.93 | 93.71 | — | — | — | |
| IRRANoise Rate=0%, Checkpoint Selection=Best2023.08 | 73.38 | 89.93 | 93.71 | 66.13 | 50.24 | — | |
| IRRAImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 73.38 | 89.93 | 93.71 | 66.13 | 50.24 | — | |
| RaSaTCLImage Enc.=TCL, Text Enc.=TCL2023.08 | 73.23 | 89.2 | 93.32 | 66.43 | — | — | |
| IRMmode=STL2023.06 | 72.8 | — | — | 65.3 | — | — | |
| PLIPBackbone=RN1012023.05 | 72.34 | — | 93.46 | — | — | — | |
| RDENoise Rate=50%, Checkpoint Selection=Best2023.08 | 71.33 | 87.41 | 91.81 | 63.5 | 47.36 | — | |
| RDENoise Rate=50%, Checkpoint Selection=Last2023.08 | 71.25 | 87.39 | 91.76 | 63.59 | 47.5 | — | |
| PLIPBackbone=RN502023.05 | 71.13 | — | 92.81 | — | — | — | |
| DECLNoise Rate=20%, Checkpoint Selection=Best2023.08 | 70.29 | 87.04 | 91.93 | 62.84 | 46.54 | — | |
| DECLNoise Rate=20%, Checkpoint Selection=Last2023.08 | 70.08 | 87.2 | 92.14 | 62.86 | 46.63 | — | |
| IRRANoise Rate=20%, Checkpoint Selection=Best2023.08 | 69.74 | 87.09 | 92.2 | 62.28 | 45.84 | — | |
| CSKTVenue=CVPR20232026.02 | 69.7 | 86.92 | 91.8 | 62.74 | — | 47.68 | |
| RaSaimage shape=256x1282023.06 | 69.6 | — | — | 63.9 | — | — | |
| CFine2026.01 | 69.57 | 85.93 | 91.15 | — | — | — | |
| CFineNoise Rate=0%, Checkpoint Selection=Best2023.08 | 69.57 | 85.93 | 91.15 | — | — | — | |
| CFineImage Enc.=CLIP-ViT, Text Enc.=BERT2023.08 | 69.57 | 85.93 | 91.15 | — | — | — | |
| IRRANoise Rate=20%, Checkpoint Selection=Last2023.08 | 69.44 | 87.09 | 92.04 | 62.16 | 45.7 | — | |
| FlexiReIDVenue=ICML20252026.02 | 69.2 | 86.43 | 91.41 | 62.47 | 48.32 | 47.86 | |
| UniReIDVenue=CVPR20232026.02 | 68.71 | 85.93 | 90.84 | — | — | — | |
| UniPTImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2023.08 | 68.5 | 84.67 | — | — | — | — | |
| LCR2SImage Enc.=RN50, Text Enc.=TextCNN2023.08 | 67.36 | 84.19 | 89.62 | 59.24 | — | — | |
| CLIP-CNoise Rate=20%, Checkpoint Selection=Best2023.08 | 66.41 | 85.15 | 90.89 | 59.36 | 43.02 | — | |
| CLIP-CNoise Rate=20%, Checkpoint Selection=Last2023.08 | 66.1 | 86.01 | 91.02 | 59.77 | 43.57 | — | |
| BEATImage Enc.=RN101, Text Enc.=BERT2023.08 | 65.61 | 83.45 | 89.54 | — | — | — | |
| IVT2026.01 | 65.59 | 83.11 | 89.21 | — | — | — | |
| LVTVenue=ECCV20222026.02 | 65.59 | 83.11 | 89.21 | — | — | — | |
| IVTNoise Rate=0%, Checkpoint Selection=Best2023.08 | 65.59 | 83.11 | 89.21 | — | — | — | |
| IVTImage Enc.=ViT-Base, Text Enc.=BERT2023.08 | 65.59 | 83.11 | 89.21 | — | — | — | |
| PBSLImage Enc.=RN50, Text Enc.=BERT2023.08 | 65.32 | 83.81 | 89.26 | — | — | — | |
| MLLMEmbed-ReIDQuery-Gallery feature type (C2C/E2E/E2C)=C2C2026.02 | 65.29 | 82.22 | 87.56 | 62.92 | 52.11 | 51.8 | |
| LGURVenue=MM20222026.02 | 65.25 | 83.12 | 89 | — | — | — | |
| LGURImage Enc.=DeiT-Small, Text Enc.=BERT2023.08 | 65.25 | 83.12 | 89 | — | — | — | |
| DECLNoise Rate=50%, Checkpoint Selection=Best2023.08 | 65.22 | 83.72 | 89.28 | 57.94 | 41.39 | — | |
| DECLNoise Rate=50%, Checkpoint Selection=Last2023.08 | 65.09 | 83.58 | 89.26 | 57.89 | 41.35 | — | |
| RDENoise=80%, Checkpoint Selection Strategy=Best2023.08 | 64.99 | 83.15 | 89.52 | 57.84 | 41.07 | — | |
| RDENoise=80%, Checkpoint Selection Strategy=Last2023.08 | 64.91 | 83.2 | 89.54 | 57.83 | 41.07 | — | |
| AXM-NetImage Enc.=RN50, Text Enc.=BERT2023.08 | 64.44 | 80.52 | 86.77 | 58.73 | — | — | |
| CAIBCVenue=MM20222026.02 | 64.43 | 82.87 | 87.35 | — | — | — | |
| CAIBCImage Enc.=RN50, Text Enc.=BERT2023.08 | 64.43 | 82.87 | 88.37 | — | — | — | |
| TIPCB2026.01 | 64.26 | 83.19 | 89.1 | — | — | — | |
| TIPCBVenue=NeurIPS20222026.02 | 64.26 | 83.19 | 89.1 | — | — | — | |
| TIPCBImage Enc.=RN50, Text Enc.=BERT2023.08 | 64.26 | 83.19 | 89.1 | — | — | — | |
| SAF2026.01 | 64.13 | 82.62 | 88.4 | — | — | — | |
| SAFVenue=ICASSP20222026.02 | 64.13 | 82.62 | 88.4 | 58.61 | — | 42.73 | |
| SAFImage Enc.=ViT-Base, Text Enc.=BERT2023.08 | 64.13 | 82.62 | 88.4 | — | — | — | |
| SAF2023.06 | 64.1 | — | — | 58.6 | — | — | |
| PSLD2023.06 | 64.1 | — | — | 60.1 | — | — | |
| Han et al.Image Enc.=CLIP-RN101, Text Enc.=CLIP-Xformer2023.08 | 64.08 | 81.73 | 88.19 | 60.08 | — | — | |
| SRCF2026.01 | 64.04 | 82.99 | 88.81 | — | — | — | |
| LBUL+BERTVenue=MM20222026.02 | 64.04 | 82.66 | 87.22 | — | — | — | |
| LBULImage Enc.=RN50, Text Enc.=BERT2023.08 | 64.04 | 82.66 | 87.22 | — | — | — | |
| CLIP-CNoise Rate=50%, Checkpoint Selection=Best2023.08 | 64.02 | 83.66 | 89.38 | 57.33 | 40.9 | — | |
| CLIP-CNoise Rate=50%, Checkpoint Selection=Last2023.08 | 63.97 | 83.74 | 89.54 | 57.35 | 40.88 | — | |
| ISANetImage Enc.=RN50, Text Enc.=LSTM2023.08 | 63.92 | 82.15 | 87.69 | — | — | — | |
| LapscoreImage Enc.=RN50, Text Enc.=BERT2023.08 | 63.4 | — | 87.8 | — | — | — | |
| BLIPBackbone=ViT-L2023.05 | 63.23 | — | 88.74 | — | — | — | |
| IRRANoise Rate=50%, Checkpoint Selection=Best2023.08 | 62.41 | 82.23 | 88.4 | 55.52 | 38.48 | — | |
| SSAN2026.01 | 61.37 | 80.15 | 86.73 | — | — | — | |
| SSANNoise Rate=0%, Checkpoint Selection=Best2023.08 | 61.37 | 80.15 | 86.73 | — | — | — | |
| SSANImage Enc.=RN50, Text Enc.=LSTM2023.08 | 61.37 | 80.15 | 86.73 | — | — | — | |
| BLIPBackbone=ViT-B2023.05 | 60.37 | — | 86.63 | — | — | — | |
| ALBEF2023.06 | 60.3 | — | — | 56.7 | — | — | |
| DSSLVenue=MM20212026.02 | 59.98 | 80.41 | 87.56 | — | — | — | |
| DSSLImage Enc.=RN50, Text Enc.=BERT2023.08 | 59.98 | 80.41 | 87.56 | — | — | — | |
| NAFS2026.01 | 59.94 | 79.86 | 86.7 | — | — | — | |
| LUPBackbone=RN1522023.05 | 59.41 | — | 86.22 | — | — | — | |
| NAFSImage Enc.=RN50, Text Enc.=BERT2023.08 | 59.36 | 79.13 | 86 | 54.07 | — | — | |
| LUP-NLBackbone=RN1522023.05 | 59.27 | — | 86.06 | — | — | — | |
| CLIPBackbone=ViT-B2023.05 | 58.91 | — | 86.21 | — | — | — | |
| MLLMEmbed-ReIDQuery-Gallery feature type (C2C/E2E/E2C)=E2C2026.02 | 58.8 | 77.35 | 84.98 | 58.03 | 47.87 | 47.55 | |
| BaselineBackbone=RN1522023.05 | 58.64 | — | 85.84 | — | — | — | |
| IVTNoise Rate=20%, Checkpoint Selection=Best2023.08 | 58.59 | 78.51 | 85.61 | 57.19 | 45.78 | — | |
| LUP-NLBackbone=RN1012023.05 | 58.06 | — | 85.64 | — | — | — | |
| CLIPBackbone=RN1012023.05 | 58.04 | — | 85.88 | — | — | — | |
| CLIPBackbone=RN502023.05 | 57.92 | — | 85.12 | — | — | — | |
| SOLIDERBackbone=Swin-B2023.05 | 57.85 | — | 84.97 | — | — | — |