Two-Speed Deep-Learning Ensemble for Classification of Incremental Land-Cover Satellite Image Patches

High-velocity data streams present a challenge to deep learning-based computer vision models due to the resources needed to retrain for new incremental data. This study presents a novel staggered training approach using an ensemble model comprising the following: (i) a resource-intensive high-accuracy vision transformer; and (ii) a fast training, but less accurate, low parameter-count convolutional neural network. The vision transformer provides a scalable and accurate base model. A convolutional neural network (CNN) quickly incorporates new data into the ensemble model. Incremental data are simulated by dividing the very large So2Sat LCZ42 satellite image dataset into four intervals. The CNN is trained every interval and the vision transformer trained every half interval. We call this combination of a complementary ensemble with staggered training a two-speed network. The novelty of this approach is in the use of a staggered training schedule that allows the ensemble model to efficiently incorporate new data by retraining the high-speed CNN in advance of the resource-intensive vision transformer, thereby allowing for stable continuous improvement of the ensemble. Additionally, the ensemble models for each data increment out-perform each of the component models, with best accuracy of 65% against a holdout test partition of the RGB version of the So2Sat dataset.

Automated summary

This study introduces a novel staggered training approach that combines a high-accuracy vision transformer and a low-parameter-count convolutional neural network in an ensemble model. The ensemble model efficiently incorporates new data and allows for continuous improvement through a staggered training schedule.