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 1905.03540cs.CV
收藏

利用注意力地图将人类知识嵌入深度神经网络

Embedding Human Knowledge into Deep Neural Network via Attention Map

Chubu University(中部大学);ABEJA Inc.(ABEJA公司)

Masahiro Mitsuhara, Hiroshi Fukui, Yusuke Sakashita, Takanori Ogata, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

摘要:

在这项工作中,我们的目标是实现一种将人类知识嵌入深度神经网络的方法。虽然嵌入人类知识的传统方法已被应用于非深度机器学习,但由于模型参数数量巨大,将其应用于深度学习模型具有挑战性。为了解决这个问题,我们专注于注意分支网络(ABN)的注意力机制。在本文中,我们提出了一种微调方法,利用单通道的注意力地图,这是手动编辑的人类专家。我们的微调方法可以训练一个网络,使输出的注意力地图对应于编辑的。因此,经过微调的网络可以输出一个考虑到人类知识的注意力地图。使用ImageNet、CUB-200-2010和IDRiD的实验结果表明,可以获得清晰的注意力图进行视觉解释,并提高分类性能。我们的研究结果可以成为一个新的框架,通过人类直观的编辑,通过视觉界面优化网络,并建议人机合作的新的可能性,除了改善视觉解释。

英文摘要:

In this work, we aim to realize a method for embedding human knowledge into deep neural networks. While the conventional method to embed human knowledge has been applied for non-deep machine learning, it is challenging to apply it for deep learning models due to the enormous number of model parameters. To tackle this problem, we focus on the attention mechanism of an attention branch network (ABN). In this paper, we propose a fine-tuning method that utilizes a single-channel attention map which is manually edited by a human expert. Our fine-tuning method can train a network so that the output attention map corresponds to the edited ones. As a result, the fine-tuned network can output an attention map that takes into account human knowledge. Experimental results with ImageNet, CUB-200-2010, and IDRiD demonstrate that it is possible to obtain a clear attention map for a visual explanation and improve the classification performance. Our findings can be a novel framework for optimizing networks through human intuitive editing via a visual interface and suggest new possibilities for human-machine cooperation in addition to the improvement of visual explanations.

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。

↑