【TPAMI 2025 🔥】Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection

If you like our project, please give us a star ⭐ on GitHub for latest update.

📰 News & Update

• [2025.07.01] We released the code based on the DeViT architecture.
• [2025.04.09] Our paper was accepted by Journal IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!

🗝️ How to Run

The project includes TFA++, MFDC and DeViT folders. Please enter different folders and follow their commands to reproduce.

👍 Acknowledgement

DeViT: an open-set object detector.

FsDet: Implementations of few-shot object detection benchmarks.

MFDC: Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection, ECCV 2022.

✏️ Citation

@article{chen2025generalized,
  title={Generalized Semantic Contrastive Learning Via Embedding Side Information for Few-Shot Object Detection},
  author={Chen, Ruoyu and Zhang, Hua and Li, Jingzhi and Liu, Li and Huang, Zhen and Cao, Xiaochun},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025},
  publisher={IEEE}
}