Deep Learning Training Procedure Augmentations

원문 초록

Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis. The focus of most research directions up until very recently has been on beating state-of-the-art results. This has materialized in the utilization of bigger and bigger models and techniques which help the training procedure to extract more predictive power out of a given dataset. While this has lead to great results, many of which with real-world applications, other relevant aspects of deep learning have remained neglected and unknown. In this work, we will present several novel deep learning training techniques which, while capable of offering significant performance gains they also reveal several interesting analysis results regarding convergence speed, optimization landscape smoothness, and adversarial robustness. The methods presented in this work are the following: $\bullet$ Perfect Ordering Approximation; a generalized model agnostic curriculum learning approach. The results show the effectiveness of the technique for improving training time as well as offer some new insight into the training process of deep networks. $\bullet$ Cascading Sum Augmentation; an extension of mixup capable of utilizing more data points for linear interpolation by leveraging a smoother optimization landscape. This can be used for computer vision tasks in order to improve both prediction performance as well as improve passive model robustness.