Person Re-Identification on RegDB Visible2Infrared
96.12Rank-1 AccuracyBIT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BITre-ranking=false2026.03 | 96.12 | 92.43 | |
| MUNre-ranking=false2026.03 | 95.19 | 87.15 | |
| CMTre-ranking=false2026.03 | 95.17 | 87.3 | |
| IDKLre-ranking=true2026.03 | 94.72 | 90.19 | |
| HOS-Netre-ranking=false2026.03 | 94.7 | 90.04 | |
| CIFT†Backbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=backbone features2022.08 | 92.17 | 86.96 | |
| CIFTre-ranking=true2026.03 | 91.96 | 92 | |
| CIFTBackbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=transferred graph features2022.08 | 91.96 | 92 | |
| DEENre-ranking=false2026.03 | 91.1 | 85.1 | |
| SAAIre-ranking=false2026.03 | 91.07 | 91.45 | |
| HCTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 91.05 | 83.28 | |
| FMCNetre-ranking=false2026.03 | 89.12 | 84.43 | |
| MAUMre-ranking=false2026.03 | 87.87 | 85.09 | |
| PMTre-ranking=false2026.03 | 84.83 | 76.55 | |
| SMCLBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 83.93 | 79.83 | |
| MPANetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 83.7 | 80.9 | |
| MCLNetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 80.31 | 73.07 | |
| CIMABackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 78.8 | 69.4 | |
| cm-SSFTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 72.3 | 72 | |
| AGWBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 70.05 | 66.37 | |
| DDAGBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 69.34 | 63.46 | |
| cm-SSFT(sq)Backbone=ResNet-50, Input Resolution=288 × 1442022.08 | 65.4 | 65.6 | |
| AlignGANBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 57.9 | 53.6 | |
| JSIA-ReIDBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 48.5 | 49.3 | |
| D2RLBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 43.4 | 44.1 |