Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond
It provides practical guidance for researchers and practitioners dealing with non-standard datasets, scarce annotations, or small data, but is incremental as it compiles existing techniques.
This tutorial addresses the challenges of training deep neural networks on real-world data, such as poor generalization with small datasets, by covering basic steps and recent methods to improve models, including architectural choices and training procedures.
Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be particularly useful in datasets that are not as well-prepared as those in challenges, and also under scarce annotation and/or small data. We describe basic procedures: as data preparation, optimization and transfer learning, but also recent architectural choices such as use of transformer modules, alternative convolutional layers, activation functions, wide and deep networks, as well as training procedures including as curriculum, contrastive and self-supervised learning.