VOC2012

The main goal of this challenge is to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). It is fundamentally a supervised learning learning problem in that a training set of labelled images is provided.

搜集汇总

背景与挑战

背景概述

VOC2012是一个用于视觉对象识别的监督学习数据集，包含20个对象类别，支持分类、检测、分割和动作分类等多种竞赛任务。数据分为训练/验证和测试两部分，其中分割和动作分类数据较VOC2011有所扩充。