In recent times, except for sporadic cases, the trend in Computer Vision is to achieve minor improvements over considerable increases in complexity. To reverse this tendency, we propose a novel method to boost image classification performances without an increase in complexity. To this end, we revisited ensembling, a powerful approach, not often adequately used due to its nature of increased complexity and training time, making it viable by specific design choices. First, we trained end-to-end two EfficientNet-b0 models (known to be the architecture with the best overall accuracy/complexity trade-off in image classification) on disjoint subsets of data (i.e. bagging). Then, we made an efficient adaptive ensemble by performing fine-tuning of a trainable combination layer. In this way, we were able to outperform the state-of-the-art by an average of 0.5\% on the accuracy with restrained complexity both in terms of number of parameters (by 5-60 times), and FLoating point Operations Per Second (by 10-100 times) on several major benchmark datasets, fully embracing the green AI.
Efficient adaptive ensembling for image classification
Bruno A;Moroni D;Martinelli M
2023
Abstract
In recent times, except for sporadic cases, the trend in Computer Vision is to achieve minor improvements over considerable increases in complexity. To reverse this tendency, we propose a novel method to boost image classification performances without an increase in complexity. To this end, we revisited ensembling, a powerful approach, not often adequately used due to its nature of increased complexity and training time, making it viable by specific design choices. First, we trained end-to-end two EfficientNet-b0 models (known to be the architecture with the best overall accuracy/complexity trade-off in image classification) on disjoint subsets of data (i.e. bagging). Then, we made an efficient adaptive ensemble by performing fine-tuning of a trainable combination layer. In this way, we were able to outperform the state-of-the-art by an average of 0.5\% on the accuracy with restrained complexity both in terms of number of parameters (by 5-60 times), and FLoating point Operations Per Second (by 10-100 times) on several major benchmark datasets, fully embracing the green AI.File | Dimensione | Formato | |
---|---|---|---|
prod_468474-doc_201016.pdf
accesso aperto
Descrizione: Preprint - Efficient adaptive ensembling for image classification
Tipologia:
Versione Editoriale (PDF)
Dimensione
583.97 kB
Formato
Adobe PDF
|
583.97 kB | Adobe PDF | Visualizza/Apri |
prod_468474-doc_201393.pdf
accesso aperto
Descrizione: Efficient adaptive ensembling for image classification
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.34 MB
Formato
Adobe PDF
|
1.34 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.