Improving Robot Localisation by Ignoring Visual Distraction
Improving Robot Localisation by Ignoring Visual Distraction
复制标题
DOI：
10.1109/iros51168.2021.9636595
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Oscar Alejandro Mendez Maldonado;M. Vowels;R. Bowden
中科院分区：
文献类型：
--
作者：
Oscar Alejandro Mendez Maldonado;M. Vowels;R. Bowden
注意力是现代深度学习的重要组成部分。然而，很少有人强调它的反面：忽视分心。我们的日常生活要求我们明确地避免注意那些混淆我们试图完成的任务的显著视觉特征。这种视觉优先级使我们能够专注于重要的任务，同时忽略视觉干扰。在这项工作中，我们引入了神经盲，它使智能体能够完全忽略被视为干扰的对象或类。更明确地说，我们的目标是使神经网络完全无法在其潜在空间中表示特定的选择类。在一个非常真实的意义上，这使得网络对某些类“视而不见”，允许和代理专注于对给定任务重要的东西，并演示了如何使用它来改进本地化。
Attention is an important component of modern deep learning. However, less emphasis has been put on its inverse: ignoring distraction. Our daily lives require us to explicitly avoid giving attention to salient visual features that confound the task we are trying to accomplish. This visual prioritisation allows us to concentrate on important tasks while ignoring visual distractors.In this work, we introduce Neural Blindness, which gives an agent the ability to completely ignore objects or classes that are deemed distractors. More explicitly, we aim to render a neural network completely incapable of representing specific chosen classes in its latent space. In a very real sense, this makes the network "blind" to certain classes, allowing and agent to focus on what is important for a given task, and demonstrates how this can be used to improve localisation.