Invertible Neural Networks with Applications in Computer Vision

可逆神经网络在计算机视觉中的应用

• 批准号: 2602161
• 金额: --
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2602161
• 关键词: Invertible; Neural; Networks; Applications; Computer

The focus of the PhD project is on the development and refinement of invertible neural networks with applications in the field of computer vision. Neural networks, and convolutional neural networks in particular, have proven to be an extremely powerful tool in computer vision among many other large-scale applications. Some computer vision tasks are highly relevant to the modern insurance business, for example: (1) using damaged car images from the customers for damage detection and identification in order to expedite the motor claim process; (2) using indoor and outdoor property images to learn useful latent features to improve the modelling of home insurance pricing.Invertible Neural Networks (INNs), as compared to classical neural networks, enjoy several additional advantages. Firstly, they have the potential to achieve accuracies for large-scale applications that go well beyond standard networks. This is due to their strongly favourable memory footprint, which allows for the training of larger (deeper) networks and higher-dimensional input data as compared to standard deep learning settings. As such, INNs would enable the insurance business to scale to larger data sets hence wider applications in the global insurance business. Secondly, INNs allow for training so-called 'normalising flows' - powerful models for learning complex probability distributions from samples, which allow for both likelihood estimation as well as efficient sampling. The former is particularly applicable to risk assessment for insurance policies.While INNs are readily applicable to many applications relevant to the insurance business, they suffer from a lack of guarantees in terms of regularity and numerical stability. Without these properties, one cannot ensure that the models are trustworthy thus reliable for large-scale applications. The project thus aims to develop the regularity and stability theory of INNs further, to allow for more fine-grained stability guarantees.

博士项目的重点是可逆神经网络的开发和改进，并在计算机视觉领域应用。神经网络，特别是卷积神经网络，已被证明是计算机视觉中许多其他大规模应用中非常强大的工具。一些计算机视觉任务与现代保险业务高度相关，例如：（1）使用来自客户的受损汽车图像进行损坏检测和识别，以加快汽车索赔过程;（2）使用室内和室外财产图像来学习有用的潜在特征，以改进房屋保险定价的建模。与经典神经网络相比，享受几个额外的优势。首先，它们有潜力实现远超出标准网络的大规模应用的精度。这是由于它们非常有利的内存占用，与标准深度学习设置相比，这允许训练更大（更深）的网络和更高维的输入数据。因此，INN将使保险业务能够扩展到更大的数据集，从而在全球保险业务中得到更广泛的应用。其次，INN允许训练所谓的“归一化流”-用于从样本中学习复杂概率分布的强大模型，这允许进行似然估计和有效采样。前者特别适用于保险单的风险评估，虽然INN可随时应用于许多与保险业务有关的应用，但它们在规律性和数值稳定性方面缺乏保证。如果没有这些属性，就不能确保模型是可信的，从而在大规模应用中是可靠的。因此，该项目旨在进一步发展INN的规则性和稳定性理论，以实现更细粒度的稳定性保证。