【24h】

Learning to focus for object proposals

机译:学习专注于对象建议

获取原文
获取原文并翻译 | 示例

摘要

Object proposal generators address the wasteful exhaustive search of the sliding window scheme in visual object detection and have been shown effective. However, the number of candidate windows is still large in order to ensure full coverage of potential objects. This paper presents a complementary technique that aims to work with any proposal generating system, amending the workflow from “propose-assess” to “propose-adjust-assess”. The adjustment serves as an auto-focus mechanism for the system and reduces the number of object proposals to be processed. The auto-focus is realized by two learning-based transformation models, one translating and the other deforming the windows towards better alignments of the objects, which are trained for identifying generic objects using image cues. Experiments on reallife image data sets show that the proposed technique can reduce the number of proposals without loss of performance.
机译:对象提议生成器解决了视觉对象检测中对滑动窗口方案的浪费性穷举搜索,并且已经证明是有效的。但是,候选窗口的数量仍然很大,以确保完全覆盖潜在对象。本文提出了一种旨在与任何提案生成系统一起使用的补充技术,将工作流程从“提案评估”修改为“提案调整评估”。该调整用作系统的自动聚焦机制,并减少了要处理的对象建议的数量。通过两个基于学习的转换模型来实现自动聚焦,一个转换模型,另一个使窗口变形以使对象更好地对齐,这些模型经过训练以使用图像提示来识别通用对象。在现实生活中的图像数据集上的实验表明,所提出的技术可以减少提议的数量而不会降低性能。

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