Add challenge and further ressources

Author: nicolasreichardt

tutorial.ipynb

@@ -1458,7 +1458,82 @@
     "<a name=\"challenge\"></a>\n",
     "## ⭐ Challenge ⭐\n",
     "\n",
-    "tbd"
+    "### **Photovoltaic Capacity Estimation in France via Prototypical Network Segmentation**\n",
+    "\n",
+    "\n",
+    "### **Overview**\n",
+    "\n",
+    "This project uses a dataset containing RGB aerial imagery of buildings and landscapes, polygon segmentation masks of photovoltaic (PV) arrays, and installation metadata (location and nominal capacity) for thousands of solar installations across France.\n",
+    "\n",
+    "Your objectives are:\n",
+    "\n",
+    "1. **Segment PV arrays** in unseen aerial RGB images using the provided segmentation masks  \n",
+    "   (i.e., generate per-pixel segmentation masks of solar panels).\n",
+    "\n",
+    "2. **Compare segmentation results** with installation metadata (`metadata.csv`), which includes ground-truth installation characteristics.\n",
+    "\n",
+    "3. **Evaluate**:\n",
+    "   - **(a)** your practical application of Prototypical Network–based segmentation,  \n",
+    "   - **(b)** the model’s ability to generalize to a new dataset,  \n",
+    "   - **(c)** the accuracy of area-based PV capacity estimates when compared against reported capacities.\n",
+    "\n",
+    "You can use the following ressources to help you:\n",
+    "\n",
+    "- **Dataset**:  \n",
+    "  [Zenodo Dataset](https://zenodo.org/records/7358126)\n",
+    "\n",
+    "- **Published Paper**:  \n",
+    "  [Nature Article](https://www.nature.com/articles/s41597-023-01951-4)\n",
+    "\n",
+    "- **GitHub Repository (tools & implementation guidance)**:  \n",
+    "  [BDAP-PV Repository](https://github.com/gabrielkasmi/bdappv)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a name=\"Further Ressources\"></a>\n",
+    "## Further Ressources\n",
+    "\n",
+    "### **Foundational Papers**\n",
+    "\n",
+    "- **Shaban, A., Bansal, S., Liu, Z., Essa, I., & Boots, B. (2017).** One-Shot Learning for Semantic Segmentation. *BMVC.*  \n",
+    "  [https://doi.org/10.48550/arXiv.1709.03410](https://doi.org/10.48550/arXiv.1709.03410)  \n",
+    "  → First paper to formally define the few-shot semantic segmentation task.  \n",
+    "  → Introduces a conditioning branch that generates segmentation parameters from support examples.\n",
+    "\n",
+    "- **Snell, J., Swersky, K., & Zemel, R. (2017).** Prototypical Networks for Few-Shot Learning. *Advances in Neural Information Processing Systems (NeurIPS 2017), Vol. 30.*  \n",
+    "  [https://doi.org/10.48550/arXiv.1703.05175](https://doi.org/10.48550/arXiv.1703.05175)  \n",
+    "  → Establishes the concept of class prototypes derived from support embeddings.  \n",
+    "  → Influences nearly all metric-based few-shot segmentation methods.\n",
+    "\n",
+    "- **Wang, K., Liew, J. H., Zou, Y., Zhou, D., & Feng, J. (2019).** PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment. *ICCV.*  \n",
+    "  [https://doi.org/10.48550/arXiv.1908.06391](https://doi.org/10.48550/arXiv.1908.06391)  \n",
+    "  → Introduces prototype alignment networks to better utilize support-set information.  \n",
+    "  → Serves as a strong and efficient baseline for few-shot segmentation.\n",
+    "\n",
+    "- **Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., & Jia, J. (2020).** Prior Guided Feature Enrichment Network for Few-Shot Segmentation. *IEEE TPAMI, 44*(2), 1050–1065.  \n",
+    "  [https://doi.org/10.1109/TPAMI.2020.3013717](https://doi.org/10.1109/TPAMI.2020.3013717)  \n",
+    "  → Introduces PFENet, significantly improving generalization.  \n",
+    "  → Set a new benchmark after PANet for high-performance few-shot segmentation.\n",
+    "\n",
+    "### **Other Ressources**\n",
+    "\n",
+    "- **Code of the original implementation of Prototypical Networks (Snell et al., 2017)**  \n",
+    "  https://github.com/jakesnell/prototypical-networks\n",
+    "\n",
+    "- **Video explanation of Prototypical Networks (deep dive into concepts + code)**  \n",
+    "  https://www.youtube.com/watch?v=rHGPfl0pvLY\n",
+    "\n",
+    "- **Comprehensive GitHub repository on many few-shot learning techniques**  \n",
+    "  https://github.com/sicara/easy-few-shot-learning?tab=readme-ov-file\n",
+    "\n",
+    "- **Transformer-based state-of-the-art segmentation: YOLOE (Zero-shot detection & segmentation)**  \n",
+    "  https://github.com/THU-MIG/yoloe\n",
+    "\n",
+    "- **Transformer-based state-of-the-art segmentation: SAM Models (Segment Anything Model — Meta AI)**  \n",
+    "  https://github.com/facebookresearch/segment-anything\n"
    ]
   },
   {
@@ -1468,9 +1543,29 @@
     "<a name=\"references\"></a>\n",
     "## References\n",
     "\n",
-    "- ...\n",
-    "- ...\n",
-    "- ..."
+    "- Alsentzer, E., Li, M. M., Kobren, S. N., Noori, A., Undiagnosed Diseases Network, Kohane, I. S., & Zitnik, M. (2025). Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases. *npj Digital Medicine, 8*(1), 380. [https://doi.org/10.1038/s41746-025-01749-1](https://doi.org/10.1038/s41746-025-01749-1)\n",
+    "\n",
+    "- Castello, R., Walch, A., Attias, R., Cadei, R., Jiang, S., & Scartezzini, J.-L. (2021). Quantification of the suitable rooftop area for solar panel installation from overhead imagery using convolutional neural networks. *Journal of Physics: Conference Series, 2042*(1), 012002. [https://doi.org/10.1088/1742-6596/2042/1/012002](https://doi.org/10.1088/1742-6596/2042/1/012002)\n",
+    "\n",
+    "- Chen, Y., Wei, C., Wang, D., Ji, C., & Li, B. (2022). Semi-supervised contrastive learning for few-shot segmentation of remote sensing images. *Remote Sensing, 14*(17), 4254. [https://doi.org/10.3390/rs14174254](https://doi.org/10.3390/rs14174254)\n",
+    "\n",
+    "- Ding, H., Zhang, H., & Jiang, X. (2022). Self-regularized prototypical network for few-shot semantic segmentation. *Pattern Recognition, 132*, 109018. [https://doi.org/10.1016/j.patcog.2022.109018](https://doi.org/10.1016/j.patcog.2022.109018)\n",
+    "\n",
+    "- Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. In *International Conference on Machine Learning* (pp. 1126–1135). PMLR. [https://doi.org/10.48550/arXiv.1703.03400](https://doi.org/10.48550/arXiv.1703.03400)\n",
+    "\n",
+    "- Ge, Z., Fan, X., Zhang, J., & Jin, S. (2025). SegPPD-FS: Segmenting plant pests and diseases in the wild using few-shot learning. *Plant Phenomics*, 100121. [https://doi.org/10.1016/j.plaphe.2025.100121](https://doi.org/10.1016/j.plaphe.2025.100121)\n",
+    "\n",
+    "- Hu, Y., Liu, C., Li, Z., Xu, J., Han, Z., & Guo, J. (2022). Few-shot building footprint shape classification with relation network. *ISPRS International Journal of Geo-Information, 11*(5), 311. [https://doi.org/10.3390/ijgi11050311](https://doi.org/10.3390/ijgi11050311)\n",
+    "\n",
+    "- Jadon, S. (2021, February). COVID-19 detection from scarce chest x-ray image data using few-shot deep learning approach. In *Medical Imaging 2021: Imaging Informatics for Healthcare, Research, and Applications* (Vol. 11601, pp. 161–170). SPIE. [https://doi.org/10.1117/12.2581496](https://doi.org/10.1117/12.2581496)\n",
+    "\n",
+    "- Lee, G. Y., Dam, T., Ferdaus, M. M., Poenar, D. P., & Duong, V. (2025). Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ATTBHFA-Net. *arXiv preprint arXiv:2510.18326.* [https://doi.org/10.48550/arXiv.2510.18326](https://doi.org/10.48550/arXiv.2510.18326)\n",
+    "\n",
+    "- Li, X., He, Z., Zhang, L., Guo, S., Hu, B., & Guo, K. (2025). CDCNet: Cross-domain few-shot learning with adaptive representation enhancement. *Pattern Recognition, 162*, 111382. [https://doi.org/10.1016/j.patcog.2025.111382](https://doi.org/10.1016/j.patcog.2025.111382)\n",
+    "\n",
+    "- Puthumanaillam, G., & Verma, U. (2023). Texture based prototypical network for few-shot semantic segmentation of forest cover: Generalizing for different geographical regions. *Neurocomputing, 538*, 126201. [https://doi.org/10.1016/j.neucom.2023.03.062](https://doi.org/10.1016/j.neucom.2023.03.062)\n",
+    "\n",
+    "- Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P. H., & Hospedales, T. M. (2018). Learning to compare: Relation network for few-shot learning. In *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition* (pp. 1199–1208). [https://doi.org/10.1109/CVPR.2018.00131](https://doi.org/10.1109/CVPR.2018.00131)\n"
    ]
   }
  ],