CODaN: Common Objects Day and Night, an image classification dataset.

Common Objects Day and Night (CODaN) is an image classification dataset for zero-shot day-night domain adaptation / generalization.<br>The CODaN dataset consists of 15,500 224x224 colour images in 10 classes, with 1,550 images per class. There are 10,000 training images, 500 validation images, 2,500 daytime test images and 2,500 nighttime test images.<br>The dataset is collected from the excellent COCO, ImageNet and ExDark datasets. All images are filtered and cropped such that they have the same dimensions and are completely mutually exclusive, i.e. do not contain objects of different classes, nor do belong objects to multiple classes.

昼夜通用物体数据集（Common Objects Day and Night，缩写为CODaN）是一款面向零样本（Zero-shot）昼夜域自适应与泛化任务的图像分类数据集。该数据集共包含10个分类下的15500张224×224分辨率彩色图像，每个分类对应1550张图像。其中训练集含10000张图像，验证集含500张，日间测试集与夜间测试集各含2500张图像。本数据集源自优质的COCO、ImageNet及ExDark数据集。所有图像均经过筛选与裁剪处理，以确保尺寸统一且完全互斥：即单张图像中不会包含不同类别的物体，且单个物体也不会被归属于多个类别。

搜集汇总

背景与挑战

背景概述

CODaN是一个专为零样本昼夜域适应设计的图像分类数据集，包含15,500张统一尺寸的彩色图像，分为10个类别。该数据集从COCO、ImageNet和ExDark中精选而来，确保图像互斥且类别纯净。