oxford-iiit-pet

# The Oxford-IIIT Pet Dataset

## Description
A 37 category pet dataset with roughly 200 images for each class. The images have a large variations in scale, pose and lighting.

This instance of the dataset uses standard label ordering and includes the standard train/test splits. Trimaps and bbox are not included, but there is an `image_id` field that can be used to reference those annotations from official metadata.

Website: https://www.robots.ox.ac.uk/~vgg/data/pets/

## Citation
```bibtex
@InProceedings{parkhi12a,
author = "Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman and C. V. Jawahar",
title = "Cats and Dogs",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition",
year = "2012",
}
```

# 牛津-IIIT宠物数据集（Oxford-IIIT Pet Dataset）

## 数据集说明
该数据集涵盖37个宠物类别，每类别配备约200张图像。所有图像在尺度、拍摄姿态与光照环境上均存在较大差异。

本版本数据集采用标准标签排序规则，并内置标准训练/测试划分方案。未提供三掩码图（Trimap）与边界框（bbox），但增设`image_id`字段，可用于从官方元数据中关联调取对应标注。

## 官网地址
https://www.robots.ox.ac.uk/~vgg/data/pets/

## 引用格式
bibtex
@InProceedings{parkhi12a,
author = "Omkar M. Parkhi and Andrea Vedaldi and Andrew Zisserman and C. V. Jawahar",
title = "猫狗",
booktitle = "IEEE计算机视觉与模式识别会议",
year = "2012",
}

搜集汇总

背景与挑战

背景概述

该数据集包含37个宠物类别，每类约有200张图像，这些图像在尺度、姿态和光照方面具有显著变化。它提供了标准的训练/测试划分，适用于计算机视觉任务。