Abstract
Large scale datasets created from user labels or openly available data have become crucial to provide training data for large scale learning algorithms. While these datasets are easier to acquire, the data are frequently noisy and unreliable, which is motivating research on weakly supervised learning techniques. In this paper we propose an iterative learning method that extracts the useful information from a large scale change detection dataset generated from open vector data to train a fully convolutional network which surpasses the performance obtained by naive supervised learning. We also propose the guided anisotropic diffusion algorithm, which improves semantic segmentation results using the input images as guides to perform edge preserving filtering, and is used in conjunction with the iterative training method to improve results.
Abstract (translated)
从用户标签或公开可用数据创建的大规模数据集对于为大规模学习算法提供培训数据变得至关重要。虽然这些数据集更容易获取,但数据往往是噪声大、不可靠的,这促使人们对弱监督学习技术的研究。本文提出了一种迭代学习方法,从开放向量数据生成的大规模变化检测数据集中提取有用信息,从而训练出一个完全卷积的网络,该网络的性能优于原始监督学习。我们还提出了一种引导各向异性扩散算法,该算法以输入图像为指导,改进了语义分割结果,并结合迭代训练方法对结果进行了改进。
URL
https://arxiv.org/abs/1904.08208