Fine-grained Attribute Recognition on SLIP-RS Constructed Benchmark Vehicle
23.93Purpose mAPSLIP-RS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SLIP-RSBackbone=ConvNeXT-L, Training data=RS-Attribute-15M2026.05 | 23.93 | 31.35 | |
| SLIP-RSBackbone=ConvNeXT-T, Training data=RS-Attribute-15M2026.05 | 23.9 | 28.8 | |
| SLIP-RSBackbone=ConvNeXT-T, Training data=RS-Attribute-O2026.05 | 19.36 | 24.72 | |
| OpenRSDBackbone=RTMDet-L, Training data=ORSD+2026.05 | 15.53 | 18.35 | |
| LAE-DINOBackbone=Swin-T, Training data=LAE-1M2026.05 | 14.74 | 12.31 |