we claim that we utilise ONE single model to perform all the evaluations to simulate driving scenarios in real life.
| methods | mIoU (class) |
|---|---|
| closed seg. [paper] [code] | 82.46 [report] |
| dense-hybrid [paper] [code] | 82.06 [report] |
| meta-ood [paper] [code] | 81.51 [report] |
| pebal [paper] [code] | 81.19 [report] |
| ours | 82.46 [report] |
you can reproduce our results based on the supported checkpoints below:
for the segment-me-if-you-can (SMIYC), download the official evaluation code (with an extra post-process stage) to achieve the reported performance. we support the prediction & results in here.
- you can download our training log via this LINK.
- for more details, you can check our wandb log in this
LINK,
where it includes:
overall information (e.g., training command line, hardware information and training time).
training details (e.g., loss curves, validation results and visualization)
output logs (well, sometimes might crash ...)
- in the final training stage, we adopt longer training epochs and more frequent validation to choose the potential best model for black boxing test sets.