Semantic Segmentation on Cityscapes 1024x2048px
81.92mIoUDINOv3
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DINOv3Size(Spec)=7B, Latency (ms)=316.79, Throughput (samples/s)=3.262026.05 | 81.92 | 96.44 | |
| JetViT-DINOv3Size(Spec)=7B (2 FA), Latency (ms)=221.08, Throughput (samples/s)=4.802026.05 | 81.92 | 96.45 | |
| JetViT-DINOv3Size(Spec)=Large (2 FA), Latency (ms)=18.77, Throughput (samples/s)=57.902026.05 | 79.88 | 96.08 | |
| DINOv3Size(Spec)=Large, Latency (ms)=35.07, Throughput (samples/s)=29.532026.05 | 79.84 | 96.07 | |
| AM-RADIO v3Size(Spec)=Large, Latency (ms)=33.24, Throughput (samples/s)=31.152026.05 | 78.5 | 95.78 | |
| AM-RADIO v3Size(Spec)=Base, Latency (ms)=12.08, Throughput (samples/s)=87.592026.05 | 76.43 | 95.37 | |
| JetViT-DINOv3Size(Spec)=Base (2 FA), Latency (ms)=8.27, Throughput (samples/s)=133.682026.05 | 75.01 | 95.3 | |
| DINOv3Size(Spec)=Base, Latency (ms)=12.86, Throughput (samples/s)=81.522026.05 | 74.56 | 95.19 | |
| JetViT-DINOv3Size(Spec)=Base (1 FA), Latency (ms)=7.69, Throughput (samples/s)=145.452026.05 | 74.5 | 95.2 | |
| JetViT-DINOv3Size(Spec)=Base (0 FA), Latency (ms)=7.37, Throughput (samples/s)=153.942026.05 | 71.87 | 94.75 |