CAMO-FS Dataset

CAMO-FS Dataset comes with the paper entitled The Art of Camouflage: Few-shot Learning for Animal Detection and Segmentation, IEEE Access, 2024. Authors: Thanh-Danh Nguyen, Anh-Khoa Nguyen Vu, Nhat-Duy Nguyen, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Minh-Triet Tran, Tam V. Nguyen*. DOI: https://doi.org/10.1109/ACCESS.2024.3432873 ArXiv version: https://arxiv.org/abs/2304.07444 Official GitHub Source Code: https://github.com/danhntd/FS-CDIS The dataset includes 2852 camouflaged images (images.zip) and few-shot annotations in COCO JSON format (few-shot-annotations.zip). We also release a script to play around with the data samples.CAMO-FS 数据集附带论文《伪装的艺术：动物检测与分割的少样本学习》，发表于IEEE Access，2024年。 作者：Thanh-Danh Nguyen, Anh-Khoa Nguyen Vu, Nhat-Duy Nguyen, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Minh-Triet Tran, Tam V. Nguyen*。 DOI：https://doi.org/10.1109/ACCESS.2024.3432873 ArXiv版本：https://arxiv.org/abs/2304.07444 官方GitHub源代码：https://github.com/danhntd/FS-CDIS 该数据集包含2852张伪装图像（images.zip）以及COCO JSON格式的少样本标注（few-shot-annotations.zip）。此外，我们还发布了一个脚本，以便用户对数据样本进行交互式操作。