Transfer learning is a deep-learning technique that ameliorates the problem of learning when human-annotated labels are expensive and limited. In place of such labels, it uses instead the previously trained weights from a well-chosen source model as the initial weights for the training of a base model for a new target dataset. We demonstrate a novel but general technique for automatically creating such source models. We generate pseudo-labels according to an efficient and extensible algorithm that is based on a classical result from the geometry of high dimensions, the Cayley-Menger determinant. This G2L (``geometry to label'') method incrementally builds up pseudo-labels using a greedy computation of hypervolume content. We demonstrate that the method is tunable with respect to expected accuracy, which can be forecast by an information-theoretic measure of dataset similarity (divergence) between source and target. The results of 280 experiments show that this mechanical technique generates base models that have similar or better transferability compared to a baseline of models trained on extensively human-annotated ImageNet1K labels, yielding an overall error decrease of 0.43\%, and an error decrease in 4 out of 5 divergent datasets tested.
翻译:转移学习是一种深层次的学习技术,在人类附加标签昂贵且有限的情况下,可以缓解学习问题。替代这种标签,它使用以前经过训练的精选源模型的重量,作为培训新目标数据集基础模型的初始重量。我们展示了一种创新但一般的自动创建这种源模型的技术。我们根据一个高效和可扩展的算法产生假标签,该算法以高维的几何(Cayley-Meanger决定因素)的经典结果为基础。这个G2L(对标签的“测量”方法)使用贪婪高容量内容的计算方法,逐步建立假标签。我们证明,该方法与预期准确性有关,可以通过对源和目标之间类似数据(维度)的信息理论性测量来预测。 280项实验结果显示,这种机械技术产生基础模型,与经过广泛人类附加说明的图像Net1K标签培训的模型基准相比,具有相似或更好的可转移性。我们证明,该方法在预期的准确性方面具有缓冲性,可以通过对源和目标之间类似性(维度)的模型进行总体误差减少0.43和数据减少4差差。