Megvii-BaseDetection / Megvii-BaseDetection/OTA
论文疑问
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 246
- Forks
- 24
- PR merge metrics
- No merged PRs in 30d
Description
很感谢这篇很棒的论文！
但在阅读的时候有一些疑惑希望得到解答：
（1）在对ATSS, PAA进行对比模糊anchor处理试验的时候，比如figure3，table2， 想问下这两者的模糊anchor定义是什么呢？ OTA给了一个阈值0.9进行判断，但这两者不清楚；
（2）想问下是否全文的sinkhorn算法涉及到的公示，Si求和的上界是不是应该等于m+1呢？比如eq.1.
期待解答，谢谢
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the paper's ATSS and PAA comparisons, including Figure 3 and Table 2, to identify how fuzzy anchors are defined. Then check the Sinkhorn equations around Eq. 1, focusing on the upper bound of the S_i summation. Done means providing a documented, evidence-based answer to both questions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100