Person Re-Identification on RegDB Infrared2Visible
94.22Rank-1 AccuracyIDKL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IDKLre-ranking=true2026.03 | 94.22 | 90.43 | |
| BITre-ranking=false2026.03 | 93.65 | 93.54 | |
| HOS-Netre-ranking=false2026.03 | 93.3 | 89.2 | |
| SAAIre-ranking=false2026.03 | 92.09 | 92.01 | |
| CMTre-ranking=false2026.03 | 91.97 | 84.46 | |
| MUNre-ranking=false2026.03 | 91.86 | 85.01 | |
| CIFTre-ranking=true2026.03 | 90.3 | 90.78 | |
| CIFTBackbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=transferred graph features2022.08 | 90.3 | 90.78 | |
| CIFT†Backbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=backbone features2022.08 | 90.12 | 84.81 | |
| DEENre-ranking=false2026.03 | 89.5 | 83.4 | |
| HCTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 89.3 | 81.46 | |
| FMCNetre-ranking=false2026.03 | 88.38 | 83.86 | |
| MAUMre-ranking=false2026.03 | 86.95 | 84.34 | |
| PMTre-ranking=false2026.03 | 84.16 | 75.13 | |
| SMCLBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 83.05 | 78.57 | |
| MPANetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 82.8 | 80.7 | |
| CIMABackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 77.9 | 69.4 | |
| MCLNetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 75.93 | 69.49 | |
| cm-SSFTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 71 | 71.7 | |
| DDAGBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 68.06 | 61.8 | |
| cm-SSFT(sq)Backbone=ResNet-50, Input Resolution=288 × 1442022.08 | 63.8 | 64.2 | |
| AlignGANBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 56.3 | 53.4 | |
| JSIA-ReIDBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 48.1 | 48.9 |