Gratulation an Lukas Miklautz @lumik777, Preisträger des Award of Excellence – Staatspreis für die besten Dissertationen 🌟 Zur Dissertation "Prototype-based representation learning with deep clustering" 👉 https://t.co/z0BK1ZK0Xf 📸 BMBWF/Fotografie Sabine Klimpt/Lichtblick KG

MIM-Refiner: a self-supervised method to efficiently pre-train large-scale vision models, that sets a new SOTA on a broad range of datasets/tasks by refining masked image models (MIM, e.g. MAE or data2vec) with an instance discrimination objective (ID, e.g. SimCLR or DINO).

Read the great paper made by three #DoCSunivie students, Lukas Miklautz (@lumik777), who presented it at the @icdm2022 in Orlando, Martin Teuffenbach & Pascal Weber, along with Walid Durani, Rona Perjuci, Christian Bohm, and Prof. Claudia Plant: https://t.co/gjc7trvOwB🤩@csunivie