1 code implementation • 1 Nov 2020 • Victor Zuanazzi, Joris van Vugt, Olaf Booij, Pascal Mettes
This work proposes a metric learning approach for self-supervised scene flow estimation.
no code implementations • 14 Aug 2018 • Joris van Vugt, Elena Marchiori, Ritse Mann, Albert Gubern-Mérida, Nikita Moriakov, Jonas Teuwen
We analyze two transfer learning settings: 1) unsupervised transfer, where Hologic data with soft lesion annotation at pixel level and Siemens unlabelled data are used to annotate images in the latter data; 2) weak supervised transfer, where exam level labels for images from the Siemens mammograph are available.