<b>Underwater datasets for MADNet</b>

The underwater datasets used for MADNet are Brackish, UOv2, and RUOD.File: UOv2.zip<b>Description:</b> It contains five target categories: echinus, holothurian, scallop, starfish, and waterweeds. The dataset is divided into a training set of 5,320 samples, a validation set of 1,520 samples, and a test set of 760 samples, following a 7:2:1 ratio.File: Brackish.zip<b>Description:</b> The dataset, which contains 14,674 images of crabs, fish, jellyfish, shrimp, small fish, and starfish, was randomly divided into a training set, a validation set, and a test set in an 8:1:1 ratio, comprising 11,739, 1,467, and 1,468 images, respectively.File: RUOD.zip<b>Description:</b> It contains 14,000 images with 10 target categories, namely holothurian, echinus, scallop, starfish, fish, corals, diver, cuttlefish, turtle, and jellyfish. It is divided into 9,800 images with 51,934 annotations for the training set and 4,200 images with 22,969 annotations for the validation set, respectively. A total of 300 images were provided in the test set, comprising 100 images each for blur, color, and light.<br>Data was derived from the following sources:Brackish: https://universe.roboflow.com/brad-dwyer/brackish-underwaterUOv2: https://universe.roboflow.com/roboflow-100/underwater-objects-5v7p8RUOD: https://drive.google.com/file/d/1hxtbdgfVveUm_DJk5QXkNLokSCTa_E5o/view?usp=drive_link

用于MADNet的水下数据集包含Brackish、UOv2及RUOD三个数据集。
文件：UOv2.zip<b>描述：</b>该数据集涵盖5类目标，分别为海胆（echinus）、海参（holothurian）、扇贝（scallop）、海星（starfish）与水草（waterweeds）。数据集按照7:2:1的比例划分为训练集（5320个样本）、验证集（1520个样本）及测试集（760个样本）。
文件：Brackish.zip<b>描述：</b>该数据集包含14674张图像，涵盖螃蟹、鱼类、水母、虾、小型鱼类及海星共6类目标。数据集以8:1:1的比例随机划分为训练集（11739张）、验证集（1467张）与测试集（1468张）。
文件：RUOD.zip<b>描述：</b>该数据集包含14000张图像，涵盖10类目标，分别为海参、海胆、扇贝、海星、鱼类、珊瑚、潜水员、墨鱼、海龟及水母。数据集划分为训练集与验证集：训练集包含9800张图像，共计51934个标注框；验证集包含4200张图像，共计22969个标注框。测试集共提供300张图像，其中模糊、色彩异常及光照异常场景各100张。
数据集来源如下：
Brackish: https://universe.roboflow.com/brad-dwyer/brackish-underwater
UOv2: https://universe.roboflow.com/roboflow-100/underwater-objects-5v7p8
RUOD: https://drive.google.com/file/d/1hxtbdgfVveUm_DJk5QXkNLokSCTa_E5o/view?usp=drive_link