1 code implementation • 31 May 2022 • Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz, Mina Rezaei, Bernd Bischl, Rodrigo Caye Daudt, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
We show that the idea can be extended to uncertainty quantification: by modulating the network activations of a single deep network with FiLM, one obtains a model ensemble with high diversity, and consequently well-calibrated estimates of epistemic uncertainty, with low computational overhead in comparison.
1 code implementation • 6 Apr 2021 • Mehmet Ozgur Turkoglu, Eric Brachmann, Konrad Schindler, Gabriel Brostow, Aron Monszpart
Visual re-localization means using a single image as input to estimate the camera's location and orientation relative to a pre-recorded environment.
1 code implementation • 17 Feb 2021 • Mehmet Ozgur Turkoglu, Stefano D'Aronco, Gregor Perich, Frank Liebisch, Constantin Streit, Konrad Schindler, Jan Dirk Wegner
The three-level label hierarchy is encoded in a convolutional, recurrent neural network (convRNN), such that for each pixel the model predicts three labels at different level of granularity.
1 code implementation • 4 Dec 2020 • Nando Metzger, Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
We propose to use neural ordinary differential equations (NODEs) in combination with RNNs to classify crop types in irregularly spaced image sequences.
3 code implementations • 25 Nov 2019 • Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
1 code implementation • 2 Feb 2019 • Mehmet Ozgur Turkoglu, William Thong, Luuk Spreeuwers, Berkay Kicanaoglu
The visual world we sense, interpret and interact everyday is a complex composition of interleaved physical entities.