Search Results for author: Volker Fischer

Found 22 papers, 9 papers with code

Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems

1 code implementation19 Oct 2023 David T. Hoffmann, Simon Schrodi, Jelena Bratulić, Nadine Behrmann, Volker Fischer, Thomas Brox

We designed synthetic tasks to study the problem in detail, but the leaps in performance can be observed also for language modeling and in-context learning (ICL).

In-Context Learning Language Modelling

Zero-Shot Visual Classification with Guided Cropping

no code implementations12 Sep 2023 Piyapat Saranrittichai, Mauricio Munoz, Volker Fischer, Chaithanya Kumar Mummadi

We empirically show that our approach improves zero-shot classification results across architectures and datasets, favorably for small objects.

Classification Object +3

Multi-Attribute Open Set Recognition

1 code implementation14 Aug 2022 Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, Volker Fischer

While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they cannot provide explanations indicating which underlying visual attribute(s) (e. g., shape, color or background) cause a specific sample to be unknown.

Attribute Image Classification +1

Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain

1 code implementation20 Jul 2022 Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, Volker Fischer

Our approach extends the training set with an additional dataset (the source domain), which is specifically designed to facilitate learning independent representations of basic visual factors.

Contrasting quadratic assignments for set-based representation learning

1 code implementation31 May 2022 Artem Moskalev, Ivan Sosnovik, Volker Fischer, Arnold Smeulders

The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects.

Contrastive Learning Metric Learning +1

EML Online Speech Activity Detection for the Fearless Steps Challenge Phase-III

no code implementations21 Jun 2021 Omid Ghahabi, Volker Fischer

Speech Activity Detection (SAD), locating speech segments within an audio recording, is a main part of most speech technology applications.

Action Detection Activity Detection

Does enhanced shape bias improve neural network robustness to common corruptions?

no code implementations ICLR 2021 Chaithanya Kumar Mummadi, Ranjitha Subramaniam, Robin Hutmacher, Julien Vitay, Volker Fischer, Jan Hendrik Metzen

We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.

Data Augmentation

EML System Description for VoxCeleb Speaker Diarization Challenge 2020

no code implementations23 Oct 2020 Omid Ghahabi, Volker Fischer

This technical report describes the EML submission to the first VoxCeleb speaker diarization challenge.

speaker-diarization Speaker Diarization

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

5 code implementations NeurIPS 2020 Fabian B. Fuchs, Daniel E. Worrall, Volker Fischer, Max Welling

We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations.


Group Pruning using a Bounded-Lp norm for Group Gating and Regularization

no code implementations9 Aug 2019 Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer

We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.

Grid Saliency for Context Explanations of Semantic Segmentation

2 code implementations NeurIPS 2019 Lukas Hoyer, Mauricio Munoz, Prateek Katiyar, Anna Khoreva, Volker Fischer

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions.

Image Classification Segmentation +1

Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation

no code implementations9 Oct 2018 Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke

Our filter module splits the filter task into multiple less complex and more interpretable subtasks.

Hierarchical Recurrent Filtering for Fully Convolutional DenseNets

no code implementations5 Oct 2018 Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke

Generating a robust representation of the environment is a crucial ability of learning agents.

The streaming rollout of deep networks - towards fully model-parallel execution

1 code implementation NeurIPS 2018 Volker Fischer, Jan Köhler, Thomas Pfeil

Deep neural networks, and in particular recurrent networks, are promising candidates to control autonomous agents that interact in real-time with the physical world.

Statestream: A toolbox to explore layerwise-parallel deep neural networks

no code implementations ICLR 2018 Volker Fischer

Most artificial deep neural networks are partitioned into a directed graph of connected modules or layers and the layers themselves consist of elemental building blocks, such as single units.

Universal Adversarial Perturbations Against Semantic Image Segmentation

no code implementations ICCV 2017 Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, Volker Fischer

We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs.

Image Classification Image Segmentation +2

Adversarial Examples for Semantic Image Segmentation

no code implementations3 Mar 2017 Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations.

BIG-bench Machine Learning General Classification +4

On Detecting Adversarial Perturbations

1 code implementation14 Feb 2017 Jan Hendrik Metzen, Tim Genewein, Volker Fischer, Bastian Bischoff

In this work, we propose to augment deep neural networks with a small "detector" subnetwork which is trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations.

Adversarial Attack Binary Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.