Robust model fitting is a core algorithm in several computer vision applications. Despite being studied for decades, solving this problem efficiently for datasets that are heavily contaminated by outliers is still challenging: due to the underlying computational complexity. A recent focus has been on learning-based algorithms. However, most of these approaches are supervised (which require a large amount of labelled training data). In this paper, we introduce a novel unsupervised learning framework: that learns to directly (without labelled data) solve robust model fitting. Moreover, unlike other learning-based methods , our work is agnostic to the underlying input features, and can be easily generalized to a wide variety of LP-type problems with quasi-convex residuals. We empirically show that our method outperforms existing (un)supervised learning approaches, and also achieves competitive results compared to traditional (non-learning-based) methods. Our approach is designed to try to maximise consensus (MaxCon), similar to the popular RANSAC. The basis of our approach, is to adopt a Reinforcement Learning framework. This requires designing appropriate reward functions, and state encodings. We provide a family of reward functions, tunable by choice of a parameter. We also investigate the application of different basic and enhanced Q-learning components.

中文翻译：

---

最大共识鲁棒拟合的无监督学习：一种强化学习方法

鲁棒模型拟合是多种计算机视觉应用中的核心算法。尽管已经研究了几十年，但由于潜在的计算复杂性，对于被异常值严重污染的数据集有效地解决这个问题仍然具有挑战性。最近的一个重点是基于学习的算法。然而，这些方法中的大多数都是有监督的（这需要大量标记的训练数据）。在本文中，我们介绍了一种新颖的无监督学习框架：学习直接（没有标记数据）解决鲁棒模型拟合问题。而且，与其他基于学习的方法不同，我们的工作对底层输入特征是不可知的，并且可以很容易地推广到各种具有准凸残差的 LP 类型问题。我们凭经验表明，我们的方法优于现有的（非）监督学习方法，并且与传统（非基于学习的）方法相比也取得了有竞争力的结果。我们的方法旨在尝试最大化共识 (MaxCon)，类似于流行的 RANSAC。我们方法的基础是采用强化学习框架。这需要设计适当的奖励函数和状态编码。我们提供了一系列奖励函数，可通过选择参数进行调整。我们还研究了不同基本和增强 Q 学习组件的应用。