PASCAL Visual Object Class --- PASCAL VOC数据集（最后附deeplab数据集）

最新推荐文章于 2024-07-08 14:25:28 发布

馅儿了个饼

最新推荐文章于 2024-07-08 14:25:28 发布

阅读量1k

点赞数

分类专栏：数据集，机器学习文章标签： pascal 数据机器学习

本文链接：https://blog.csdn.net/qq_36113899/article/details/77571066

版权

本文介绍了PASCAL VOC数据集的历史背景、2012版本的内容，包括20个类别和各类应用场景，如分类、检测、分割和动作分类等比赛。此外，还提及了DeepLab在实际中的实践应用。

摘要由CSDN通过智能技术生成

自从2005年开始每年举办挑战赛。官网： http://host.robots.ox.ac.uk/pascal/VOC/

用于从实际图片中识别出特定对象。

2005~2012共八个版本，目前可以使用的是2007年及其以后的版本：

年份	数据	新增	NOTE
2005	Only 4 classes: bicycles, cars, motorbikes, people. Train/validation/test: 1578 images containing 2209 annotated objects.	Two competitions: classification and detection	Images were largely taken from exising public datasets, and were not as challenging as the flickr images subsequently used. This dataset is obsolete.
2006	10 classes: bicycle, bus, car, cat, cow, dog, horse, motorbike, person, sheep. Train/validation/test: 2618 images containing 4754 annotated objects.	Images from flickr and from Microsoft Research Cambridge (MSRC) dataset	The MSRC images were easier than flickr as the photos often concentrated on the object of interest. This dataset is obsolete.