arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02265cs.CVcs.LGeess.IV
收藏

利用区域建议交互网络学习长期视觉动态

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

UC Berkeley(加州大学伯克利分校);UC San Diego(加州大学圣迭戈分校);CMU(卡内基梅隆大学)

Haozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma, Jitendra Malik

摘要:

学习长期动力学模型是理解物理常识的关键。大多数现有的从视觉输入学习动态的方法通过诉诸于短期模型的快速重新规划来回避长期预测。这不仅要求这些模型超级准确,而且还将它们限制在代理可以持续获得反馈并在每个步骤采取行动直到完成的任务上。在本文中,我们的目标是利用视觉识别任务中成功案例的想法来构建对象表示,这些对象表示可以捕获长距离的对象间和对象-环境交互。为此,我们提出了区域建议交互网络(RPIN),其中的原因,每个对象的轨迹在一个潜在的区域建议功能空间。由于简单而有效的对象表示,我们的方法在预测质量和规划下游任务的能力方面都明显优于现有方法,并且可以很好地推广到新的环境。代码、预训练模型和更多可视化结果可在https://haozhi.io/RPIN上获得。

英文摘要:

Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models. This not only requires such models to be super accurate but also limits them only to tasks where an agent can continuously obtain feedback and take action at each step until completion. In this paper, we aim to leverage the ideas from success stories in visual recognition tasks to build object representations that can capture inter-object and object-environment interactions over a long-range. To this end, we propose Region Proposal Interaction Networks (RPIN), which reason about each object's trajectory in a latent region-proposal feature space. Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin both in terms of prediction quality and their ability to plan for downstream tasks, and also generalize well to novel environments. Code, pre-trained models, and more visualization results are available at https://haozhi.io/RPIN.

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。

↑