对象持久性出现在内存中的随机漫步中
Object Permanence Emerges in a Random Walk along Memory
摘要：
本文提出了一个自我监督的目标学习表示，本地化对象的遮挡-一个属性被称为对象永久性。一个中心问题是在完全闭塞的情况下学习信号的选择。而不是直接监督的位置看不见的对象，我们提出了一个自我监督的目标，既不需要人的注释，也不假设对象的动态。我们表明，对象持久性可以出现通过优化的时间一致性的记忆：我们适合马尔可夫步行沿时空图的记忆，其中在每个时间步的状态是非马尔可夫特征的序列编码器。这导致了存储被遮挡对象并预测其运动的记忆表示，以更好地定位它们。由此产生的模型优于现有的方法在几个数据集的日益复杂和现实，尽管需要最少的监督，因此被广泛适用。
英文摘要：
This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence. A central question is the choice of learning signal in cases of total occlusion. Rather than directly supervising the locations of invisible objects, we propose a self-supervised objective that requires neither human annotation, nor assumptions about object dynamics. We show that object permanence can emerge by optimizing for temporal coherence of memory: we fit a Markov walk along a space-time graph of memories, where the states in each time step are non-Markovian features from a sequence encoder. This leads to a memory representation that stores occluded objects and predicts their motion, to better localize them. The resulting model outperforms existing approaches on several datasets of increasing complexity and realism, despite requiring minimal supervision, and hence being broadly applicable.
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。
