Biologically plausible saliency mechanisms improve feedforward object recognition
Biologically plausible saliency mechanisms improve feedforward object recognition
复制标题
DOI：
10.1016/j.visres.2010.05.034
复制
发表时间：
2010-10-01
期刊：
影响因子：
1.8
通讯作者：
Vasconcelos, Nuno
中科院分区：
文献类型：
--
作者：
Han, Sunhyoung;Vasconcelos, Nuno
研究了针对自然图像统计数据的统计推断和学习的生物学合理性。 结果表明，可以通过 V1 标准神经生理学模型的计算来实现丰富的统计决策规则、置信度测量和风险估计。 特别是，可以通过简单地重新安排横向划分连接、非线性和池化来计算不同的统计量。 通过这种重新安排，可以以生物学上合理的方式实现视觉显着性的测量 这使得能够实现包括显着性模型的生物学上合理的前馈对象识别网络 通过用显着性网络替换 HMAX 架构的第一层来说明组合注意力和识别的潜力 比较各种显着性测量，以研究 (1) 显着性是否可以显着有益于视觉识别，以及 (2) 收益取决于 关于实施的具体显着性机制 实验评估表明，显着性确实增强了识别度，但收益并非独立于显着性机制 通过将显着性等同于分类置信度的自上而下机制获得最佳结果 (C) 2010 Elsevier Ltd 保留所有权利
The biological plausibility of statistical inference and learning tuned to the statistics of natural images is investigated It is shown that a rich family of statistical decision rules confidence measures and risk estimates can be implemented with the computations attributed to the standard neurophysiological model of V1 In particular different statistical quantities can be computed through simple re-arrangement of lateral divisive connections non-linearities and pooling It is then shown that a number of proposals for the measurement of visual saliency can be implemented in a biologically plausible manner through such re-arrangements This enables the implementation of biologically plausible feedforward object recognition networks that include explicit saliency models The potential of combined attention and recognition is illustrated by replacing the first layer of the HMAX architecture with a saliency network Various saliency measures are compared to investigate whether (1) saliency can substantially benefit visual recognition and (2) the benefits depend on the specific saliency mechanisms implemented Experimental evaluation shows that saliency does indeed enhance recognition but the gains are not independent of the saliency mechanisms Best results are obtained with top-down mechanisms that equate saliency to classification confidence (C) 2010 Elsevier Ltd All rights reserved