1 code implementation • 10 Jul 2023 • Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler
We propose a more efficient training protocol that fits a linear mapping between image and text embeddings of CLIP via a closed-form solution.
1 code implementation • NeurIPS 2023 • Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.
1 code implementation • 7 Jun 2022 • Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner
We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace.
2 code implementations • 24 May 2022 • Fabian Paischer, Thomas Adler, Vihang Patil, Angela Bitto-Nemling, Markus Holzleitner, Sebastian Lehner, Hamid Eghbal-zadeh, Sepp Hochreiter
We propose to utilize a frozen Pretrained Language Transformer (PLT) for history representation and compression to improve sample efficiency.
2 code implementations • 13 Oct 2020 • Thomas Adler, Johannes Brandstetter, Michael Widrich, Andreas Mayr, David Kreil, Michael Kopp, Günter Klambauer, Sepp Hochreiter
On the few-shot datasets miniImagenet and tieredImagenet with small domain shifts, CHEF is competitive with state-of-the-art methods.
2 code implementations • ICLR 2021 • Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Thomas Adler, Lukas Gruber, Markus Holzleitner, Milena Pavlović, Geir Kjetil Sandve, Victor Greiff, David Kreil, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
The new update rule is equivalent to the attention mechanism used in transformers.
Immune Repertoire Classification Multiple Instance Learning +1
no code implementations • 30 Oct 2019 • Thomas Adler, Manuel Erhard, Mario Krenn, Johannes Brandstetter, Johannes Kofler, Sepp Hochreiter
In this work, we show that machine learning models can provide significant improvement over random search.
no code implementations • 9 Oct 2019 • Johannes Lehner, Andreas Mitterecker, Thomas Adler, Markus Hofmarcher, Bernhard Nessler, Sepp Hochreiter
We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data.
Ranked #1 on Object Detection on KITTI Cars Moderate