首页> 外文期刊>Pattern Analysis and Machine Intelligence, IEEE Transactions on >Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
【24h】

Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models

机译:走向整体场景理解:启用反馈的级联分类模型

获取原文
获取原文并翻译 | 示例

摘要

Scene understanding includes many related subtasks, such as scene categorization, depth estimation, object detection, etc. Each of these subtasks is often notoriously hard, and state-of-the-art classifiers already exist for many of them. These classifiers operate on the same raw image and provide correlated outputs. It is desirable to have an algorithm that can capture such correlation without requiring any changes to the inner workings of any classifier. We propose Feedback Enabled Cascaded Classification Models (FE-CCM), that jointly optimizes all the subtasks while requiring only a ȁC;black boxȁD; interface to the original classifier for each subtask. We use a two-layer cascade of classifiers, which are repeated instantiations of the original ones, with the output of the first layer fed into the second layer as input. Our training method involves a feedback step that allows later classifiers to provide earlier classifiers information about which error modes to focus on. We show that our method significantly improves performance in all the subtasks in the domain of scene understanding, where we consider depth estimation, scene categorization, event categorization, object detection, geometric labeling, and saliency detection. Our method also improves performance in two robotic applications: an object-grasping robot and an object-finding robot.
机译:场景理解包括许多相关的子任务,例如场景分类,深度估计,对象检测等。这些子任务中的每一个通常都非常困难,并且其中许多设备已经具有最先进的分类器。这些分类器对相同的原始图像进行操作,并提供相关的输出。期望有一种可以捕获这种相关性而无需对任何分类器的内部工作进行任何改变的算法。我们提出了反馈启用的级联分类模型(FE-CCM),该模型联合优化了所有子任务,同时只需要每个子任务的原始分类器的接口。我们使用两层级联的分类器,这些分类器是原始分类器的重复实例化,第一层的输出作为第二层的输入。我们的训练方法涉及一个反馈步骤,该步骤允许较新的分类器提供有关较早分类器应关注的错误模式的信息。我们证明了我们的方法可以显着提高场景理解领域中所有子任务的性能,其中我们考虑了深度估计,场景分类,事件分类,对象检测,几何标记和显着性检测。我们的方法还提高了两个机器人应用程序的性能:对象捕获机器人和对象发现机器人。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号