Tricks and Plugins to GBM on Images and Sequences
This work addresses the problem of high training costs and manual effort in deep learning for researchers and practitioners, though it appears incremental as it builds on existing boosting and deep learning methods.
The authors tackled the challenge of training large convolutional neural networks and transformers by proposing new algorithms that combine boosting with these architectures, resulting in superior performance and lower running time on fine-grained classification tasks.
Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years. However, millions of parameters and many blocks make them difficult to be trained, and sometimes several days or weeks are required to find an ideal architecture or tune the parameters. Within this paper, we propose a new algorithm for boosting Deep Convolutional Neural Networks (BoostCNN) to combine the merits of dynamic feature selection and BoostCNN, and another new family of algorithms combining boosting and transformers. To learn these new models, we introduce subgrid selection and importance sampling strategies and propose a set of algorithms to incorporate boosting weights into a deep learning architecture based on a least squares objective function. These algorithms not only reduce the required manual effort for finding an appropriate network architecture but also result in superior performance and lower running time. Experiments show that the proposed methods outperform benchmarks on several fine-grained classification tasks.