Megvii-BaseDetection / Megvii-BaseDetection/OTA

the shape of transport plan is (m+1)*n, the transport plan can only assign one gt to an anchor, how about the lable?

Open
#20 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
246
Forks
24
PR merge metrics
No merged PRs in 30d

Description

since the shape of the transport plan is (m+1)*n, the transport plan can only assign one gt to an anchor, how about the label? In Figure 2, the optimal transport plan only gives a clue about which gt the anchor could be assigned to, but which label (from k lables each gt contains mentioned in the paper) should be assigned to the anchor and how?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the OTA paper's discussion of Figure 2 and then inspect the repository's transport-assignment implementation. Determine how the transport plan's ground-truth assignment relates to the labels each ground truth contains; done would require a decided, documented behavior or an agreed implementation change.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.