MambaCoral-DiffDet (MMCD)

---

📝 Project Overview

MambaCoral-DiffDet (MMCD) is a robust diffusion model and knowledge distillation framework designed for coral detection in complex underwater environments. It enhances coral recognition accuracy and efficiency by incorporating state-of-the-art generative models. The code for MambaCoral-DiffDet will be made publicly available once our paper is accepted.

---

📂 Dataset Information

Original Dataset

The original dataset used in this project is available at the following link:

• SCoralDet Dataset

This dataset contains images from six coral species: Euphylliaancora, Favosites, Platygyra, Sarcophyton, Sinularia, and Wavinghand, collected from the Coral Germplasm Conservation and Breeding Center at Hainan Tropical Ocean University.

Augmented Dataset

Using the MambaCoral-DiffDet model's DGM structure, we have created an augmented dataset. The dataset now contains 1,204 images, representing an 86% increase in image quantity while using only 18% of the original images. This augmentation helps improve the robustness of coral detection models by providing a more diverse set of training images.

You can download the augmented dataset here:

• MambaCoral-DiffDet Augmented Dataset

---

Dataset Preview

To showcase the diversity of generated images, here are multiple augmented versions of the same coral species generated by the DGM (Data Generation Module).

Original Image	Generated Image 1	Generated Image 2	Generated Image 3

---

🔗 Connection with SCoralDet

This work builds upon the SCoralDet dataset and research, extending the capabilities of coral detection models by introducing advanced techniques and enhanced architectures.

---

📊 Performance Comparison of MambaCoral-DiffDet (MCDD) with SOTA Models

The table below shows a comparison of MambaCoral-DiffDet (MCDD) against state-of-the-art (SOTA) models, demonstrating its improved performance in terms of mAP, precision, recall, and computational efficiency.

Model	mAP50	mAP(50-95)	Precision	Recall	Parameters (M)	GFLOPs
MambaYOLO	0.801	0.52	0.848	0.723	6.0	13.6
RT-DETR	0.816	0.546	0.881	0.770	42.0	129.6
YOLOv8	0.790	0.503	0.782	0.738	3.0	8.1
YOLOv9	0.788	0.521	0.875	0.681	2.0	7.6
YOLOv10	0.797	0.512	0.800	0.743	2.3	6.5
YOLOv11	0.799	0.518	0.847	0.735	2.6	6.3
MCDD (Ours)	0.843	0.566	0.876	0.750	6.5	13.6

Table: Comparison of MambaCoral-DiffDet (MCDD) with state-of-the-art performance models.

---

🔍 Citation

For more details on the original dataset, refer to the paper:

@ARTICLE{lu2024scoraldet,  
         author={Lu, Zhaoxuan and Liao, Lyuchao and Xie, Xingang and Yuan, Hui},  
         title={SCoralDet: Efficient real-time underwater soft coral detection with YOLO},  
         journal={Ecological Informatics},  
         year={2024},  
         artnum={102937},  
         issn={1574-9541},  
         doi={10.1016/j.ecoinf.2024.102937},  
}  

---

🎯 Applications

This dataset and the MambaCoral-DiffDet framework can be used for:

• Coral species detection and classification
• Object detection in underwater environments
• Data augmentation using diffusion models
• Knowledge distillation for marine biology applications