Update README.md
Browse files
README.md
CHANGED
|
@@ -13,9 +13,6 @@ base_model:
|
|
| 13 |
|
| 14 |
**Domain-RAG** is a novel retrieval-augmented generative framework designed for **Cross-Domain Few-Shot Object Detection (CD-FSOD)**. We leverage large-scale vision-language models (GroundingDINO), a curated COCO-style retrieval corpus, and Flux-based background generation to synthesize diverse, domain-aware training data that enhances FSOD generalization under domain shift.
|
| 15 |
|
| 16 |
-
<p align="center">
|
| 17 |
-
<img src="assets/framework.svg" alt="DomainRAG Pipeline" width="700"/>
|
| 18 |
-
</p>
|
| 19 |
|
| 20 |
---
|
| 21 |
|
|
|
|
| 13 |
|
| 14 |
**Domain-RAG** is a novel retrieval-augmented generative framework designed for **Cross-Domain Few-Shot Object Detection (CD-FSOD)**. We leverage large-scale vision-language models (GroundingDINO), a curated COCO-style retrieval corpus, and Flux-based background generation to synthesize diverse, domain-aware training data that enhances FSOD generalization under domain shift.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
---
|
| 18 |
|