随机初始化的点云集合函数有多强大？
How Powerful Are Randomly Initialized Pointcloud Set Functions?
Autodesk Research（欧特克研究）
摘要：
我们研究了由未经训练的神经集函数产生的随机嵌入，并表明它们是强大的表示，可以很好地捕获下游任务（如分类）的输入特征，并且通常是线性可分的。我们得到了令人惊讶的结果，表明随机集函数通常可以获得接近甚至更好的准确性比完全训练的模型。我们调查的因素，影响这种嵌入的代表性力量定量和定性。
英文摘要：
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.
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。
