PASCAL VOC 2010

这个挑战的目标是从现实场景中的许多视觉对象类别中识别对象（即不是预先分割的对象）。它从根本上说是一个有监督的学习问题，因为它提供了一组标记图像的训练集。已选择的 20 个对象类别是： 人：人 动物：鸟、猫、牛、狗、马、羊 交通工具：飞机、自行车、船、公共汽车、汽车、摩托车、火车 室内：瓶子、椅子、餐桌、盆栽、沙发、电视/显示器主要比赛分为分类、检测、分割三大类；和三个“品尝者”竞赛：人物布局、动作分类和 ImageNet 大规模识别：分类/检测竞赛分类：对于 20 个类中的每一个，预测测试图像中该类示例的存在/不存在。

The goal of this challenge is to recognize objects from numerous visual object categories in real-world scenes (i.e., objects that are not pre-segmented). This is fundamentally a supervised learning problem, as a training set of labeled images is provided. The 20 selected object categories are as follows:
- People: person
- Animals: bird, cat, cow, dog, horse, sheep
- Vehicles: airplane, bicycle, boat, bus, car, motorcycle, train
- Indoor scenes: bottle, chair, dining table, potted plant, sofa, television/monitor

The main competitions are divided into three major categories: classification, detection, and segmentation. Additionally, there are three 'Taster' competitions: person layout, action classification, and ImageNet Large-Scale Recognition: Classification/Detection Competitions. For the classification task: for each of the 20 categories, predict the presence or absence of instances of that category in the test images.