论文标题
搜索概念：使用直接优化发现视觉概念
Search for Concepts: Discovering Visual Concepts Using Direct Optimization
论文作者
论文摘要
将图像的无监督分解为单个对象是利用组合性和执行符号推理的关键步骤。传统上，使用摊销的推理解决了这个问题，该推理不会超出培训数据的范围，有时可能会错过正确的分解，并且需要大量的培训数据。我们建议通过基于梯度的优化对可区分对象属性的优化和全局搜索非差异性属性的组合来查找分解。我们表明，使用直接优化更具普遍性，错过了更少的正确分解，并且通常比基于摊销推断的方法所需的数据更少。这凸显了当前使用摊销推理的当前普遍实践的弱点，这些做法可以通过整合更直接的优化元素来改善。
Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem is solved using amortized inference, which does not generalize beyond the scope of the training data, may sometimes miss correct decompositions, and requires large amounts of training data. We propose finding a decomposition using direct, unamortized optimization, via a combination of a gradient-based optimization for differentiable object properties and global search for non-differentiable properties. We show that using direct optimization is more generalizable, misses fewer correct decompositions, and typically requires less data than methods based on amortized inference. This highlights a weakness of the current prevalent practice of using amortized inference that can potentially be improved by integrating more direct optimization elements.
