This code coresponds to the DeepFusion ensembling methods presented, either in their entirety or incrementally (as parts of the methods) in the following papers:
- (upcoming paper, estimated publication date: Oct-Nov 2021) Constantin, M.G., Ştefan, L.D., Ionescu, B. (est. 2021, Oct-Nov). Exploring Deep Fusion Ensembling for Automatic Visual Interestingness Prediction. In book Human Perception of Visual Information - Psychological and Computational Perspectives, Springer International Publishing, Eds. B. Ionescu, W. Bainbridge, N. Murray.
- Constantin, M. G., Ştefan, L. D., & Ionescu, B. (2021, June). DeepFusion: Deep Ensembles for Domain Independent System Fusion. In International Conference on Multimedia Modeling (pp. 240-252). Springer, Cham.
- Constantin, M. G., Ştefan, L. D., Ionescu, B., Duong, N. Q., Demarty, C. H., & Sjöberg, M. (2021). Visual Interestingness Prediction: A Benchmark Framework and Literature Review. International Journal of Computer Vision, 1-25.
- Ştefan, L. D., Constantin, M. G., & Ionescu, B. (2020, June). System Fusion with Deep Ensembles. In Proceedings of the 2020 International Conference on Multimedia Retrieval (pp. 256-260).
This code will be refactored and moved to our lab's github account. New link will be posted here. Until then we have the 0.1 version, that we will work on and improve in readability and performance.
Thank you for your patience!