hellock / hellock/scale-time-lattice

Comparing ST-Lattice with single frame detector

Open
#4 3 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.