arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.11921cs.CV
收藏

基于逆强化学习的目标导向注意控制预测

Predicting Goal-directed Attention Control Using Inverse-Reinforcement Learning

Stony Brook University(石溪大学);Department of Psychology, Stony Brook University(石溪大学心理学系);Department of Computer Science, Stony Brook University(石溪大学计算机科学系)

Gregory J. Zelinsky, Yupei Chen, Seoyoung Ahn, Hossein Adeli, Zhibo Yang, Lihan Huang, Dimitrios Samaras, Minh Hoai

摘要:

理解目标状态如何控制行为是一个成熟的问题,可以通过机器学习的新方法进行询问。这些方法需要大的标记数据集来训练模型。为了用观察到的搜索固定来注释大规模图像数据集,我们在4,366张图像的数据集中(MS-COCO)收集了16,184个来自搜索微波炉或时钟的人的固定。然后,我们使用这个行为注释的数据集和逆强化学习(IRL)的机器学习方法来学习这两个目标的目标特定奖励函数和策略。最后,我们使用这些学习的策略来预测60个新行为搜索者(时钟= 30,微波= 30)在描绘微波炉和时钟的厨房场景的不相交测试数据集中的固定(从而控制低级别图像对比度的差异)。我们发现,IRL模型预测行为搜索效率和固定密度地图使用多个指标。此外,来自IRL模型的奖励图揭示了特定于目标的模式,这些模式不仅表明目标特征的注意力引导,而且还表明场景上下文的引导(例如,沿着墙壁固定在寻找时钟)。使用机器学习和心理意义的奖励原则,可以学习目标导向注意力控制中使用的视觉特征。

英文摘要:

Understanding how goal states control behavior is a question ripe for interrogation by new methods from machine learning. These methods require large and labeled datasets to train models. To annotate a large-scale image dataset with observed search fixations, we collected 16,184 fixations from people searching for either microwaves or clocks in a dataset of 4,366 images (MS-COCO). We then used this behaviorally-annotated dataset and the machine learning method of Inverse-Reinforcement Learning (IRL) to learn target-specific reward functions and policies for these two target goals. Finally, we used these learned policies to predict the fixations of 60 new behavioral searchers (clock = 30, microwave = 30) in a disjoint test dataset of kitchen scenes depicting both a microwave and a clock (thus controlling for differences in low-level image contrast). We found that the IRL model predicted behavioral search efficiency and fixation-density maps using multiple metrics. Moreover, reward maps from the IRL model revealed target-specific patterns that suggest, not just attention guidance by target features, but also guidance by scene context (e.g., fixations along walls in the search of clocks). Using machine learning and the psychologically-meaningful principle of reward, it is possible to learn the visual features used in goal-directed attention control.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑