论文标题
使用自我监督的对象提案重构构图概括性的策略
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
论文作者
论文摘要
我们研究如何以构图概括性学习政策。我们提出了一个两阶段的框架，该框架将高级教师政策重构为具有强烈的归纳偏见的可推广的学生政策。特别是，我们实施了一个以对象为中心的学生策略，其输入对象是通过自我监管的学习从图像中学到的。从经验上讲，我们对需要组合性概括的四个困难任务评估我们的方法，并且与基线相比，取得了卓越的性能。
We study how to learn a policy with compositional generalizability. We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student policy with strong inductive bias. Particularly, we implement an object-centric GNN-based student policy, whose input objects are learned from images through self-supervised learning. Empirically, we evaluate our approach on four difficult tasks that require compositional generalizability, and achieve superior performance compared to baselines.
