论文标题
随机初始化的PointCloud设置功能的功能有多强？
How Powerful Are Randomly Initialized Pointcloud Set Functions?
论文作者
论文摘要
我们研究由未经训练的神经集功能产生的随机嵌入，并表明它们是强大的表示，可以很好地捕获下游任务（例如分类）的输入特征，并且通常可以线性分离。我们获得了令人惊讶的结果，这些结果表明，随机集合函数通常可以比完全训练的模型获得接近甚至更好的准确性。我们研究了数量和质量上影响此类嵌入的代表性力量的因素。
We study random embeddings produced by untrained neural set functions, and show that they are powerful representations which well capture the input features for downstream tasks such as classification, and are often linearly separable. We obtain surprising results that show that random set functions can often obtain close to or even better accuracy than fully trained models. We investigate factors that affect the representative power of such embeddings quantitatively and qualitatively.
