Q-learning of sequential attention for visual object recognition from informative local descriptors
Q-learning of sequential attention for visual object recognition from informative local descriptors
复制标题
从信息丰富的局部描述符中进行视觉对象识别的顺序注意力的 Q 学习
DOI：
10.1145/1102351.1102433
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
["L. Paletta
中科院分区：
文献类型：
--
作者：
["L. Paletta
这项工作为使用三个处理阶段的体系结构提供了一个在现实世界视觉对象识别中学习顺序关注的框架。第一阶段根据信息理论显着性措施拒绝了无关的本地描述符，从而提供了感兴趣的焦点（FOI）的候选者。第二阶段使用代码手册匹配器调查了FOI中的信息，并提供弱对象假设。第三阶段通过关注的转移来整合局部信息，从而导致描述术对链的链，这些链的表征对象歧视。然后，Q学习者从熵搜索和评估反馈中适应了注意序列的降低，最终优先考虑导致描述术扫描的几何形状的变化，而描述符的几何形状相对于对象识别是高度歧视的。该方法在室内（COIL-20数据库）和室外（TSG-20数据库）图像上成功评估，通过学习表明，在识别准确性和处理时间方面胜过基于本地描述的标准描述符的方法。
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects irrelevant local descriptors based on an information theoretic saliency measure, providing candidates for foci of interest (FOI). The second stage investigates the information in the FOI using a codebook matcher and providing weak object hypotheses. The third stage integrates local information via shifts of attention, resulting in chains of descriptor-action pairs that characterize object discrimination. A Q-learner adapts then from explorative search and evaluative feedback from entropy decreases on the attention sequences, eventually prioritizing shifts that lead to a geometry of descriptor-action scanpaths that is highly discriminative with respect to object recognition. The methodology is successfully evaluated on indoors (COIL-20 database) and outdoors (TSG-20 database) imagery, demonstrating significant impact by learning, outperforming standard local descriptor based methods both in recognition accuracy and processing time.