PASCAL VOC2012

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）。它基本上是一个监督学习问题，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 将有两个主要比赛和两个较小规模的“品尝者”比赛。内容：提供的训练数据由一组图像组成；每个图像都有一个注释文件，为图像中存在的 20 个类别之一中的每个对象提供一个边界框和对象类别标签。请注意，来自多个类的多个对象可能出现在同一图像中。

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

There will be two main competitions and two smaller-scale "taster" competitions.

Content: The provided training data comprises a collection of images; each image is accompanied by an annotation file that provides a bounding box and object category label for every object belonging to one of the 20 aforementioned categories present in that image. Note that multiple objects from multiple categories may appear within a single image.

搜集汇总

背景与挑战

背景概述

PASCAL VOC2012是一个用于物体检测和实例分割的计算机视觉数据集，包含20个类别的标注图像，适用于监督学习任务。数据集由牛津大学等机构于2012年发布，广泛应用于视觉对象识别研究。