Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
关于Decoupled Head的求教！
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
大家好，小白请教一个问题。旷视在2020年的一篇CVPR中提到在R-CNN实验中发现：在Head中FC适合做分类任务，Conv适合定位任务。那为什么在YOLOX的Head中两个任务都使用了Conv，而没有在分类任务中使用FC？？？
图片：
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
This is a conceptual question about why YOLOX's decoupled head uses convolution for both classification and localization, rather than requesting a specific code change. Read the YOLOX head implementation and compare it with the cited R-CNN/CVPR discussion; done means providing a clear, evidence-based explanation of the architectural choice.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100