Visible-Infrared Person Re-identification on SYSU-MM01 Indoor-search Single-shot
81.82Rank-1 AccuracyCIFT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CIFTBackbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=transferred graph features2022.08 | 81.82 | 85.61 | |
| CIFT†Backbone=ResNet-50, Input Resolution=288 × 144, Inference Feature Type=backbone features2022.08 | 78.65 | 82.11 | |
| MPANetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 76.74 | 80.95 | |
| MCLNetBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 72.56 | 76.58 | |
| cm-SSFTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 70.5 | 72.6 | |
| SMCLBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 68.84 | 75.56 | |
| CIMABackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 66.6 | 74.7 | |
| HCTBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 63.41 | 68.17 | |
| DDAGBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 61.02 | 67.98 | |
| HCBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 59.74 | 64.91 | |
| cm-SSFT(sq)Backbone=ResNet-50, Input Resolution=288 × 1442022.08 | 57.4 | 59.1 | |
| AGWBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 54.17 | 62.97 | |
| AlignGANBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 45.9 | 54.3 | |
| JSIA-ReIDBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 43.8 | 52.9 | |
| cmGANBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 31.63 | 42.19 | |
| Zero-PadBackbone=ResNet-50, Input Resolution=288 × 1442022.08 | 20.58 | 26.92 |