arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15439cs.CVq-bio.NC
收藏

基于CNN的搜索模型低估了简单视觉特征的注意力引导

CNN-based search model underestimates attention guidance by simple visual features

Endel Poder

摘要:

最近,Zhang等人(2018)提出了一种有趣的注意力引导模型,该模型使用卷积神经网络学习的视觉特征进行对象识别。我将这个模型用于搜索实验,并将准确性作为性能的衡量标准。对我们先前发表的特征和连接搜索实验的模拟表明,基于CNN的搜索模型大大低估了简单视觉特征对人类注意力的引导。一个简单的解释是,该模型没有自下而上的注意力指导。另一种观点可能是,标准的CNN不会学习类似人类的注意力引导所需的特征。

英文摘要:

Recently, Zhang et al. (2018) proposed an interesting model of attention guidance that uses visual features learnt by convolutional neural networks for object recognition. I adapted this model for search experiments with accuracy as the measure of performance. Simulation of our previously published feature and conjunction search experiments revealed that CNN-based search model considerably underestimates human attention guidance by simple visual features. A simple explanation is that the model has no bottom-up guidance of attention. Another view might be that standard CNNs do not learn features required for human-like attention guidance.

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。

↑