|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
# LongD-CLIP |
|
|
# Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation |
|
|
|
|
|
📄 **CVPR 2025** |
|
|
|
|
|
This repository provides resources for our CVPR 2025 paper: |
|
|
**"Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation"** |
|
|
|
|
|
--- |
|
|
|
|
|
## 🔍 Introduction |
|
|
|
|
|
Our work focuses on **improving CLIP’s ability to handle long-text inputs** while retaining its original knowledge. |
|
|
We propose a **Dual-Teacher Distillation** framework that: |
|
|
- Retains knowledge from the original CLIP, |
|
|
- Enhances long-text representations through teacher guidance, |
|
|
|
|
|
This work **extends the research line of [Long-CLIP](https://github.com/beichenzbc/Long-CLIP)** and further advances long-text representation learning in multimodal models. |
|
|
👉 The implementation can also **refer to [LongD-CLIP](https://github.com/yourname/LongD-CLIP)**. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 Resources |
|
|
|
|
|
- **Paper**: [CVPR 2025 proceedings](https://openaccess.thecvf.com/content/CVPR2025/papers/Feng_Retaining_Knowledge_and_Enhancing_Long-Text_Representations_in_CLIP_through_Dual-Teacher_CVPR_2025_paper.pdf) |
|
|
- **Model Weights**: [Hugging Face – LongD-CLIP](https://huggingface.co/BruceFeng98/LongD-CLIP/tree/main) |
|
|
- **Related Codebase**: [Long-CLIP](https://github.com/beichenzbc/Long-CLIP) |
|
|
|
|
|
--- |
|
|
|
