Fighting Ageism in datasets: How not to oversample images using GANs
Kamil Pluciński ⋅ Hanna Klimczak
2021 Contributed Talk 3
in
Workshop: Journal of Opportunities, Unexpected limitations, Retrospectives, Negative results, and Experiences
in
Workshop: Journal of Opportunities, Unexpected limitations, Retrospectives, Negative results, and Experiences
Abstract
In this paper, we introduce a method for dealing with imbalance in data based on SMOTE oversampling and GAN generated images. We assess the change of performance across different methods and discuss the results of the experiments. We also take an attempt of explaining why this method did not succeed to open the discussion on GAN-based resampling methods.
Video
Chat is not available.
Successful Page Load