Classification on Roadside LiDAR dataset (test)
62Mean F1CLIP-L-14
Evaluation results
| Method | Links | |
|---|---|---|
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=302026.02 | 62 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=302026.02 | 61 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=202026.02 | 61 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=202026.02 | 60 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=162026.02 | 60 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=162026.02 | 59 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=82026.02 | 57 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=302026.02 | 56 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=302026.02 | 56 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=162026.02 | 55 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=202026.02 | 55 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=202026.02 | 55 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=82026.02 | 54 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=162026.02 | 54 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=82026.02 | 52 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=82026.02 | 51 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=42026.02 | 50 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=42026.02 | 48 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=302026.02 | 47 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=42026.02 | 46 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=202026.02 | 45 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=42026.02 | 45 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=302026.02 | 44 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=162026.02 | 44 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=162026.02 | 43 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=202026.02 | 43 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=22026.02 | 43 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=82026.02 | 40 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=82026.02 | 39 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=22026.02 | 39 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=42026.02 | 37 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=22026.02 | 37 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=22026.02 | 37 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=42026.02 | 34 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=12026.02 | 32 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=22026.02 | 31 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=12026.02 | 31 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=22026.02 | 30 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=12026.02 | 30 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=12026.02 | 29 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=12026.02 | 25 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=12026.02 | 24 | |
| EVA02-L-14Image Generation=Original (without smoothing), Shots=02026.02 | 8 | |
| EVA02-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=02026.02 | 8 | |
| CLIP-B-32Image Generation=Original (without smoothing), Shots=02026.02 | 5 | |
| CLIP-B-32Image Generation=Proposed Depth-Aware (with smoothing), Shots=02026.02 | 5 | |
| CLIP-L-14Image Generation=Original (without smoothing), Shots=02026.02 | 2 | |
| CLIP-L-14Image Generation=Proposed Depth-Aware (with smoothing), Shots=02026.02 | 2 |