MCG-NJU / MCG-NJU/Structured-Sparse-RCNN
question about "Transformer" in Table 4
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 64
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for great work! I really enjoyed reading your paper.
I found that "Transformer" in Table 4 is very strong baseline, and you also provide detailed analysis versus proposed Structured Sparse R-CNN in appendix. However I cannot find how "Transformer" model is built on Sparse R-CNN backbone(it cites "Attention is All you need" paper).
Is it two-stage model(like motif) or one-stage? How was feature used for predicting relation between object pairs? Can you explain it in detail or can I find in anywhere in code?
Thanks!
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 with Table 4 and the appendix analysis mentioned in the issue, then inspect the repository for the Transformer implementation. Done means providing a clear explanation of whether the model is one- or two-stage, how it uses the Sparse R-CNN backbone, and how object-pair features are used for relation prediction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100