Learning Multi-Instance Deep Ranking and Regression Network for Visual House Appraisal
Learning Multi-Instance Deep Ranking and Regression Network for Visual House Appraisal
复制标题
DOI：
10.1109/tkde.2018.2791611
复制
发表时间：
2018-08
影响因子：
8.9
通讯作者：
Xiaobai Liu;Qian Xu;Jingjie Yang;Jacob Thalman;Shuicheng Yan;Jiebo Luo
中科院分区：
文献类型：
--
作者：
Xiaobai Liu;Qian Xu;Jingjie Yang;Jacob Thalman;Shuicheng Yan;Jiebo Luo
本文提出了一种用于房屋视觉评估问题的弱监督回归模型，该模型的目的是根据房屋的照片和文字描述(如卧室数量)来预测房屋的价值。我们的方法的核心思想是一个多层神经网络，称为多实例深度排名和回归(MiDRR)网，它共同解决了多实例环境下的两个耦合任务：排名和回归。该网络是使用弱监督数据来训练的，这不需要密集的人工注释。我们还设计了一套人类启发式算法，通过对解空间施加限制来促进深层特征，例如，有三个卧室的房子往往比只有两个卧室的房子有更高的价值。虽然这些约束是特定于所研究的问题的，但所开发的公式可以很容易地推广到其他回归应用。为了测试和评估的目的，我们收集了一个全面的房屋图像基准，其中包括来自美国最近交易的30,000套房屋的90,000张照片，并应用所提出的MiDRR网络来预测房屋价值。广泛的评估和比较表明，更多地使用图像数据以及人类启发式方法可以显著提高系统性能，并且所提出的MiDRR网络的性能明显优于替代方法。
This paper presents a weakly supervised regression model for the visual house appraisal problem, which aims to predict the value of a house from its photos and textual descriptions (e.g., number of bedrooms). The key idea of our approach is a multi-layer neural network, called multi-instance Deep Ranking and Regression (MiDRR) net, which jointly solves two coupled tasks: ranking and regression, in the multiple instance setting. The network is trained using weakly supervised data, which do not require intensive human annotations. We also design a set of human heuristics to promote deep features through imposing constraints over the solution space, e.g., a house with three bedrooms often has a higher value than that with only two bedrooms. While these constraints are specific to the studied problem, the developed formula can be easily generalized to the other regression applications. For test and evaluation purposes, we collect a comprehensive house image benchmark that includes 900,000 photos from 30,000 houses recently traded in the USA, and apply the proposed MiDRR net to predict house values. Extensive evaluations with comparisons demonstrate that additional usage of imagery data as well as human heuristics can significantly boost system performance and that the proposed MiDRR net clearly outperforms the alternative methods.