自信息神经网络结构学习
Self-informed neural network structure learning
摘要：
我们研究的问题，大规模，多标签的视觉识别与大量的可能类。我们提出了一种方法，用于增强训练的神经网络分类器的辅助能力的方式，旨在显着改善已经表现良好的模型，同时最小限度地影响其计算足迹。使用网络本身的预测作为评估视觉相似性的描述符，我们定义了一个分区的标签空间成组的视觉相似的实体。然后，我们用辅助隐藏层路径来增强网络，这些路径只与这些标签单元组相连。我们报告了一个显着的改进，在一个大规模的对象识别任务的平均精度与增强模型，而增加的乘法加法的数量不到3%。
英文摘要：
We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its computational footprint. Using the predictions of the network itself as a descriptor for assessing visual similarity, we define a partitioning of the label space into groups of visually similar entities. We then augment the network with auxilliary hidden layer pathways with connectivity only to these groups of label units. We report a significant improvement in mean average precision on a large-scale object recognition task with the augmented model, while increasing the number of multiply-adds by less than 3%.
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。
