CAREER: Non-Parametric Image Parsing

职业：非参数图像解析

• 批准号: 1149633
• 负责人: Robert Fergus
• 金额: $ 50万
• 依托单位: New York University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-03-01 至 2019-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1149633&HistoricalAwards=false
• 关键词: CAREER; Non; Parametric; Image; Parsing

This project develops new techniques for visually interpreting an image in a way that specifically leverages large image collections, now common on the web and elsewhere. The research team uses an approach whose performance directly scales with the size of the dataset, unlike many existing approaches to image understanding. The basic approach is to build a copy of a query image by assembling pieces of image from a large set of training images, in the manner of a jigsaw. Each region in the query is classified by copying labels from the matched regions. The larger the training set, the more jigsaw pieces there are to choose from, thus the more accurate the match.The initial work of the project focuses on developing efficient methods for performing the matching that allow the incorporating of various desirable constraints. The approach is then extended to handle training data with incomplete labels -- important since few datasets have labels for every region. The research plan also includes building better embeddings for the regions which place semantically similar regions closer together than current representations do, and developing efficient binary matching schemes along with further work on the region embeddings. Robust techniques for visual recognition have widespread applicability, in such areas as image search, robotics and surveillance. The project also involves extensive outreach activities, including high-school internships and the organization of a NY-area vision day for students and researchers

这个项目开发了一种新的技术，以一种特别利用大型图像集合的方式来直观地解释图像，现在在网络和其他地方很常见。研究小组使用了一种方法，其性能直接与数据集的大小成比例，这与许多现有的图像理解方法不同。基本方法是以拼图的方式，通过将大量训练图像中的图像片段组装起来，构建查询图像的副本。查询中的每个区域通过复制匹配区域的标签进行分类。训练集越大，可以选择的拼图块就越多，匹配就越准确。该项目的初始工作侧重于开发执行匹配的有效方法，以允许合并各种期望的约束。然后将该方法扩展到处理具有不完整标签的训练数据——这很重要，因为很少有数据集为每个区域都有标签。研究计划还包括为区域构建更好的嵌入，使语义相似的区域比当前的表示更紧密地放在一起，并开发有效的二进制匹配方案以及对区域嵌入的进一步研究。稳健的视觉识别技术在图像搜索、机器人和监视等领域具有广泛的适用性。该项目还涉及广泛的外展活动，包括高中实习和为学生和研究人员组织纽约地区愿景日