公开(公告)号：US20090083332A1

公开(公告)日：2009-03-26

申请号：US12234159

申请日：2008-09-19

Applicant: Ritendra Datta ,  Dhiraj Joshi ,  Jia Li ,  James Z. Wang

Inventor： Ritendra Datta ,  Dhiraj Joshi ,  Jia Li ,  James Z. Wang

IPC: G06F17/30

CPC classification number: G06K9/6263 ,  G06F16/58

Abstract: A principled, probabilistic approach to meta-learning acts as a go-between for a ‘black-box’ image annotation system and its users. Inspired by inductive transfer, the approach harnesses available information, including the black-box model's performance, the image representations, and a semantic lexicon ontology. Being computationally ‘lightweight.’ the meta-learner efficiently re-trains over time, to improve and/or adapt to changes. The black-box annotation model is not required to be re-trained, allowing computationally intensive algorithms to be used. Both batch and online annotation settings are accommodated. A “tagging over time” approach produces progressively better annotation, significantly outperforming the black-box as well as the static form of the meta-learner, on real-world data.

Abstract translation: 元学习的原则性，概率性方法作为“黑盒子”图像注释系统及其用户的一个中介。 灵感来自感性传递，该方法利用了可用的信息，包括黑箱模型的性能，图像表示和语义词典本体。 在计算上“轻量级”。 元学习者随着时间的推移有效地重新训练，以改善和/或适应变化。 黑箱注释模型不需要重新训练，允许使用计算密集型算法。 批量和在线注释设置都可以收录。 随着时间的推移，“标记”方法可以逐渐更好的注释，显着优于实体数据的黑盒子和元学习者的静态形式。