Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels

1 code implementation • 23 Oct 2020 • Valentyn Melnychuk, Evgeniy Faerman, Ilja Manakov, Thomas Seidl

Furthermore, our experiments show that exponential moving average (EMA) of model parameters, which is a component of both algorithms, is not needed for our classification problem, as disabling it leaves the outcome unchanged.

Retinal OCT Disease Classification Semi-Supervised Image Classification +1

Walking the Tightrope: An Investigation of the Convolutional Autoencoder Bottleneck

1 code implementation • 18 Nov 2019 • Ilja Manakov, Markus Rohm, Volker Tresp

We believe that the findings in this paper are directly applicable and will lead to improvements in models that rely on CAEs.

Outlier Detection Representation Learning +1

Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

1 code implementation • 7 Oct 2019 • Ilja Manakov, Markus Rohm, Christoph Kern, Benedikt Schworm, Karsten Kortuem, Volker Tresp

We cast the problem of image denoising as a domain translation problem between high and low noise domains.

Image Denoising Translation

Push it to the Limit: Discover Edge-Cases in Image Data with Autoencoders

1 code implementation • 7 Oct 2019 • Ilja Manakov, Volker Tresp

In this paper, we focus on the problem of identifying semantic factors of variation in large image datasets.