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 1701.07398cs.CVcs.AI
收藏

在人工视觉系统中学习注意力模型

Learning an attention model in an artificial visual system

Technion – Israel Institute of Technology(以色列理工学院)

Alon Hazan, Yuval Harel, Ron Meir

摘要:

人类对世界的视觉感知是一个巨大的固定图像,非常详细和清晰。然而,视网膜中的受体密度并不均匀:称为中央凹的小中心区域非常密集,并且具有高分辨率,而其周围的周边区域具有低得多的空间分辨率。因此,与我们的看法相反,我们只能以高分辨率观察视线周围的一个非常小的区域。完整和稳定视图的感知由注意力机制辅助,该注意力机制将眼睛引导到场景内的许多兴趣点。眼睛在这些目标之间快速无意识地移动,称为“扫视”。一旦目标位于中央凹的中心,眼睛就会注视几分之一秒,而视觉系统则会提取必要的信息。基于强化学习协议内的完全递归神经网络集构建人工视觉系统,并学习在解决分类任务的同时关注感兴趣的区域。该模型与几个实验观察到的现象是一致的,并提出了新的预测。

英文摘要:

The Human visual perception of the world is of a large fixed image that is highly detailed and sharp. However, receptor density in the retina is not uniform: a small central region called the fovea is very dense and exhibits high resolution, whereas a peripheral region around it has much lower spatial resolution. Thus, contrary to our perception, we are only able to observe a very small region around the line of sight with high resolution. The perception of a complete and stable view is aided by an attention mechanism that directs the eyes to the numerous points of interest within the scene. The eyes move between these targets in quick, unconscious movements, known as "saccades". Once a target is centered at the fovea, the eyes fixate for a fraction of a second while the visual system extracts the necessary information. An artificial visual system was built based on a fully recurrent neural network set within a reinforcement learning protocol, and learned to attend to regions of interest while solving a classification task. The model is consistent with several experimentally observed phenomena, and suggests novel predictions.

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。

↑