Hierarchical Attention Networks
Hierarchical Attention Networks
复制标题
DOI：
--
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
P. H. Seo;Zhe L. Lin;Scott D. Cohen;Xiaohui Shen;Bohyung Han
中科院分区：
文献类型：
--
作者：
P. H. Seo;Zhe L. Lin;Scott D. Cohen;Xiaohui Shen;Bohyung Han
我们提出了一种新颖的注意力网络，它通过多个阶段准确地关注图像中不同尺度和形状的目标对象。所提出的网络使多层能够估计卷积神经网络(CNN)中的注意力。该分层注意模型使用多个CNN层上的渐进注意过程来逐渐抑制输入图像中的无关区域。每一层中的细心过程决定是传递还是抑制用于下一卷积的特征映射。我们使用局部上下文来估计每个位置的注意力概率，因为仅通过观察单个位置的特征向量很难推断出准确的注意力。在人工数据集和真实数据集上的实验表明，该注意网络在各种属性预测任务中的表现优于传统的注意方法。
We propose a novel attention network, which accurately attends to target objects of various scales and shapes in images through multiple stages. The proposed network enables multiple layers to estimate attention in a convolutional neural network (CNN). The hierarchical attention model gradually suppresses irrelevant regions in an input image using a progressive attentive process over multiple CNN layers. The attentive process in each layer determines whether to pass or suppress feature maps for use in the next convolution. We employ local contexts to estimate attention probability at each location since it is difficult to infer accurate attention by observing a feature vector from a single location only. The experiments on synthetic and real datasets show that the proposed attention network outperforms traditional attention methods in various attribute prediction tasks.