arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.01015cs.LGcs.CV
收藏

传感器转换注意力网络

Sensor Transformation Attention Networks

Institute of Neuroinformatics(神经信息学研究所);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院)

Stefan Braun, Daniel Neil, Enea Ceolini, Jithendar Anumula, Shih-Chii Liu

摘要:

最近关于序列到序列映射的编码器-解码器模型的研究表明,将时间和空间注意力机制集成到神经网络中可以大大提高系统的性能。在这项工作中,我们报告的注意力信号的应用程序上的时间和空间区域的输入,而是作为一种方法之间的切换输入本身。我们评估了在传感器中存在动态噪声的情况下注意力切换的特殊作用,并展示了注意力信号如何动态响应环境中不断变化的噪声水平,以在三个常用的数据集TIDIGITS,华尔街日报和GRID中实现音频和视觉任务的性能提高。此外,所提出的传感器转换网络架构自然引入了许多值得探索的优点,包括易于向现有架构添加新传感器,注意力可解释性以及在训练期间看不到的各种噪声环境中的鲁棒性。最后,我们证明了仅在小TIDIGITS数据集上训练的模型的传感器选择注意力机制可以直接转移到在华尔街日报数据集上训练的预先存在的更大的网络,保持传感器之间的切换功能,以在存在噪声的情况下大幅减少错误。

英文摘要:

Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially. In this work, we report on the application of an attentional signal not on temporal and spatial regions of the input, but instead as a method of switching among inputs themselves. We evaluate the particular role of attentional switching in the presence of dynamic noise in the sensors, and demonstrate how the attentional signal responds dynamically to changing noise levels in the environment to achieve increased performance on both audio and visual tasks in three commonly-used datasets: TIDIGITS, Wall Street Journal, and GRID. Moreover, the proposed sensor transformation network architecture naturally introduces a number of advantages that merit exploration, including ease of adding new sensors to existing architectures, attentional interpretability, and increased robustness in a variety of noisy environments not seen during training. Finally, we demonstrate that the sensor selection attention mechanism of a model trained only on the small TIDIGITS dataset can be transferred directly to a pre-existing larger network trained on the Wall Street Journal dataset, maintaining functionality of switching between sensors to yield a dramatic reduction of error in the presence of noise.

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。

↑