Abstract
Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data. In this paper, we study whether CL can be applied to complex geometry problems like estimating monocular Visual Odometry (VO). Unlike existing CL approaches, we present a novel CL strategy for learning the geometry of monocular VO by gradually making the learning objective more difficult during training. To this end, we propose a novel geometry-aware objective function by jointly optimizing relative and composite transformations over small windows via bounded pose regression loss. A cascade optical flow network followed by recurrent network with a differentiable windowed composition layer, termed CL-VO, is devised to learn the proposed objective. Evaluation on three real-world datasets shows superior performance of CL-VO over state-of-the-art feature-based and learning-based VO.
Abstract (translated)
在人类和动物认知过程的启发下,课程学习(cl)通过逐渐增加训练数据的难度来训练模型。本文研究了cl是否适用于单目视觉里程计(vo)估计等复杂几何问题。与现有的认知学习方法不同,我们提出了一种新的认知学习策略,通过逐步使学习目标在训练过程中变得更加困难来学习单眼视觉器官的几何结构。为此,我们提出了一种新的几何感知目标函数,通过有界姿态回归损失联合优化小窗口上的相对变换和复合变换。本文设计了一个级联光流网络,接着是一个具有可微窗口组成层的循环网络,称为cl-vo,以了解这一目标。对三个真实数据集的评估表明,cl-vo的性能优于最先进的基于特征和基于学习的vo。
URL
https://arxiv.org/abs/1903.10543