hellock / hellock/scale-time-lattice
Comparing ST-Lattice with single frame detector
Open
- Dominant language
- No language data
- Stars
- 207
- Forks
- 25
- PR merge metrics
- No merged PRs in 30d
Description
In the performance graph, is the single frame detector shown as "Dense Detection"?
If yes, why ST-Lattice can achieve much better mAP compared to single frame detector?
For DFF, the most time consuming method is to degrade to a single frame detector. But it seems that ST-Lattice achieves much better mAP than that case as well. Any insights on how this is achieved?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.