arXiv 2109.078552021-09-16cs.CVcs.GR

通过生成三维虚拟环境评估持续学习算法

Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments

University of Florence（佛罗伦萨大学）；University of Siena（锡耶纳大学）

Enrico Meloni, Alessandro Betti, Lapo Faggi, Simone Marullo, Matteo Tiezzi, Stefano Melacci

备注：: 8 pages, 7 figures, accepted at the 1st International Workshop on Continual Semi-Supervised Learning (CSSL) @ IJCAI 2021

摘要：

持续学习是指人类和动物在特定环境中随着时间的推移而逐渐学习的能力。试图在机器中模拟这种学习过程是一项具有挑战性的任务，这也是因为在为设计现实世界中典型的持续进化动力学创造条件方面存在固有的困难。许多现有的研究工作通常涉及到静态图像或短视频数据集上的虚拟代理的训练和测试，考虑不同的学习任务序列。然而，为了设计在更现实的条件下运行的持续学习算法，获得丰富的、完全可定制的和可控的实验场地是至关重要的。专注于视觉的具体情况下，我们因此建议利用最新的进展，在3D虚拟环境中，以接近自动生成的潜在的终身动态场景与照片般逼真的外观。场景由沿着不同路线移动的对象组成，这些对象具有不同的完全可定制的时间，并且随机性也可以包括在它们的演变中。本文的一个新颖的元素是，场景中描述的参数化的方式，从而使用户能够完全控制代理感知的输入流的视觉复杂性。这些一般原则是具体实施利用最近公布的3D虚拟环境。用户可以生成场景，而不需要在计算机图形学方面有很强的技能，因为所有的生成设施都通过一个简单的高级Python接口公开。我们公开分享拟议的发电机。

英文摘要：

Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating conditions for designing continuously evolving dynamics that are typical of the real-world. Many existing research works usually involve training and testing of virtual agents on datasets of static images or short videos, considering sequences of distinct learning tasks. However, in order to devise continual learning algorithms that operate in more realistic conditions, it is fundamental to gain access to rich, fully customizable and controlled experimental playgrounds. Focussing on the specific case of vision, we thus propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially life-long dynamic scenes with photo-realistic appearance. Scenes are composed of objects that move along variable routes with different and fully customizable timings, and randomness can also be included in their evolution. A novel element of this paper is that scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives. These general principles are concretely implemented exploiting a recently published 3D virtual environment. The user can generate scenes without the need of having strong skills in computer graphics, since all the generation facilities are exposed through a simple high-level Python interface. We publicly share the proposed generator.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文