arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.09400cs.CV
收藏

AttentionRNN:一种结构化的空间注意力机制

AttentionRNN: A Structured Spatial Attention Mechanism

University of British Columbia(不列颠哥伦比亚大学)

Siddhesh Khandelwal, Leonid Sigal

摘要:

视觉注意力机制已被证明是许多现代深度神经架构的重要组成部分。它们提供了一种有选择地利用视觉信息的有效途径,这在多模态学习任务中特别有价值。然而,所有先前的注意力框架都缺乏对注意力变量之间的结构依赖关系进行明确建模的能力,这使得难以预测一致的注意力掩码。在本文中,我们开发了一种新的结构化空间注意力机制,它是端到端的可训练的,可以与任何前馈卷积神经网络集成。该AttentionRNN层通过以双向光栅扫描和逆光栅扫描顺序顺序依次预测空间掩码中的注意力值来显式地对空间注意力变量实施结构。因此,每个注意力值不仅取决于本地图像或上下文信息,而且还取决于先前预测的注意力值。我们的实验表明,在各种识别任务和数据集,包括图像分类,问答和图像生成一致的定量和定性的改进。

英文摘要:

Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be especially valuable in multi-modal learning tasks. However, all prior attention frameworks lack the ability to explicitly model structural dependencies among attention variables, making it difficult to predict consistent attention masks. In this paper we develop a novel structured spatial attention mechanism which is end-to-end trainable and can be integrated with any feed-forward convolutional neural network. This proposed AttentionRNN layer explicitly enforces structure over the spatial attention variables by sequentially predicting attention values in the spatial mask in a bi-directional raster-scan and inverse raster-scan order. As a result, each attention value depends not only on local image or contextual information, but also on the previously predicted attention values. Our experiments show consistent quantitative and qualitative improvements on a variety of recognition tasks and datasets; including image categorization, question answering and image generation.

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。

↑