Fine-grained Attribute Recognition on SLIP-RS Constructed Benchmark Plane
72.04Purpose mAPSLIP-RS
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| SLIP-RSBackbone=ConvNeXT-L, Training data=RS-Attribute-15M2026.05 | 72.04 | 57.17 | 77.33 | 69.54 | 80.47 | 79.1 | |
| SLIP-RSBackbone=ConvNeXT-T, Training data=RS-Attribute-O2026.05 | 67.61 | 48.77 | 68.47 | 70.14 | 74.27 | 71.8 | |
| SLIP-RSBackbone=ConvNeXT-T, Training data=RS-Attribute-15M2026.05 | 64.85 | 52.66 | 71.33 | 62.6 | 77.06 | 76.35 | |
| OpenRSDBackbone=RTMDet-L, Training data=ORSD+2026.05 | 9.03 | 23.07 | — | — | — | — | |
| LAE-DINOBackbone=Swin-T, Training data=LAE-1M2026.05 | 1.04 | 6.32 | — | — | — | — |