Year: 2018
Type: preprint
Abstract: Biological imaging data are often partially confounded or contain unwanted variability. Examples of such phenomena include variable lighting across microscopy image captures, stain intensity variation in histological slides, and batch effects for high throughput drug screening assays. Therefore, to develop "fair" models which generalise well to unseen examples, it is crucial to learn data representations that are insensitive to nuisance factors of variation. In this paper, we present a strategy based on adversarial training, capable of learning unsupervised representations invariant to confounders. As an empirical validation of our method, we use deep convolutional autoencoders to learn unbiased cellular representations from microscopy imaging.
Source: arXiv (Cornell University)
Institutions: University of Oxford, BenevolentAI (United Kingdom)
Language: English
Subfield: Biophysics
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W2901157752