Boosting via latent representation

Abstract

Currently minor improvements in image classification tasks are achieved by significantly increasing model complexity. This trend has been ongoing for the last years and high performance models now usually have millions of parameters. Inspired by Ensemble methods, we investigate the potential of Ensemble Learning (EL) to iteratively extend an ensemble of transformers and fit a classifier (combination layer) on the transformations. A new EL algorithm is implemented as part of the EL-framework Decolearn, containing the LPboost EL-method.