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

2023-06

Horry, Michael James

Chakraborty, Subrata

Pradhan, Biswajeet

Shulka, Nagesh

Almazroui, Mansour

Journal Article

en

Publication

Springer Cham

Switzerland

10.1007/s41748-023-00343-3

une:1959.11/59112

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 efciently 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.

link

Earth Systems and Environment, v.7, p. 525-540

2509-9434

2509-9426

525

540

Attribution 4.0 International