Attend Before you Act: Leveraging human visual attention for continual learning.
arXiv: Artificial Intelligence(2018)
摘要
When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining it to build a representation from the sensory data. In this work, we explore leveraging where humans look in an image as an implicit indication of what is salient for decision making. We build on top of the UNREAL architecture in DeepMind Labu0027s 3D navigation maze environment. We train the agent both with original images and foveated images, which were generated by overlaying the original images with saliency maps generated using a real-time spectral residual technique. We investigate the effectiveness of this approach in transfer learning by measuring performance in the context of noise in the environment.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络