Conference paper Open Access

DeepFusion: Deep Ensembles for Domain Independent System Fusion

Mihai Gabriel Constantin; Liviu-Daniel Ștefan; Bogdan Ionescu

While ensemble systems and late fusion mechanisms have proven their effectiveness by achieving state-of-the-art results in various computer vision tasks, current approaches are not exploiting the power of deep neural networks as their primary ensembling algorithm, but only as inducers, i.e., systems that are used as inputs for the primary ensembling algorithm. In this paper, we propose several deep neural network architectures as ensembling algorithms with various network configurations that use dense and attention layers, an input pre-processing algorithm, and a new type of deep neural network layer denoted the Cross-Space-Fusion layer, that further improves the overall results. Experimental validation is carried out on several data sets from various domains (emotional content classification, medical data captioning) and under various evaluation conditions (two-class regression, binary classification, and multi-label classification), proving the efficiency of DeepFusion.

Files (296.4 kB)
Name Size
UPB-MMM2021.pdf
md5:cdb8154f716d33f10c470d99b2557bdd
296.4 kB Download
21
19
views
downloads
Views 21
Downloads 19
Data volume 5.6 MB
Unique views 13
Unique downloads 14

Share

Cite as