Search Results for author: Margret Keuper

Found 62 papers, 34 papers with code

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

1 code implementation20 Mar 2024 Yumeng Li, William Beluch, Margret Keuper, Dan Zhang, Anna Khoreva

Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content.

Generative Temporal Nursing Text-to-Video Generation +1

Are Vision Language Models Texture or Shape Biased and Can We Steer Them?

1 code implementation14 Mar 2024 Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Bianca Lamm, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper

If text does indeed influence visual biases, this suggests that we may be able to steer visual biases not just through visual input but also through language: a hypothesis that we confirm through extensive experiments.

Image Captioning Image Classification +3

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

1 code implementation16 Jan 2024 Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva

Current L2I models either suffer from poor editability via text or weak alignment between the generated image and the input layout.

Domain Generalization Layout-to-Image Generation +1

Improving Stability during Upsampling -- on the Importance of Spatial Context

no code implementations29 Nov 2023 Shashank Agnihotri, Julia Grabinski, Margret Keuper

While during downsampling, aliases and artifacts can be reduced by blurring feature maps, the emergence of fine details is crucial during upsampling.

Disparity Estimation Image Classification +3

Classification robustness to common optical aberrations

1 code implementation29 Aug 2023 Patrick Müller, Alexander Braun, Margret Keuper

Experiments on ImageNet show that for a variety of different pre-trained DNNs, the performance varies strongly compared to disk-shaped kernels, indicating the necessity of considering realistic image degradations.

Classification Data Augmentation +1

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition

1 code implementation21 Aug 2023 Katharina Prasse, Steffen Jung, Yuxuan Zhou, Margret Keuper

We propose a method specifically designed for hand action recognition which uses relative angular embeddings and local Spherical Harmonics to create novel hand representations.

Action Recognition Skeleton Based Action Recognition

Divide & Bind Your Attention for Improved Generative Semantic Nursing

1 code implementation20 Jul 2023 Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva

To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind.

Attribute Generative Semantic Nursing +1

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling

1 code implementation19 Jul 2023 Julia Grabinski, Janis Keuper, Margret Keuper

Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings.

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain

1 code implementation19 Jul 2023 Julia Grabinski, Janis Keuper, Margret Keuper

To facilitate such a study, several challenges need to be addressed: 1) we need an effective means to train models with large filters (potentially as large as the input data) without increasing the number of learnable parameters 2) the employed convolution operation should be a plug-and-play module that can replace conventional convolutions in a CNN and allow for an efficient implementation in current frameworks 3) the study of filter sizes has to be decoupled from other aspects such as the network width or the number of learnable parameters 4) the cost of the convolution operation itself has to remain manageable i. e. we cannot naively increase the size of the convolution kernel.

Image Classification

An Evaluation of Zero-Cost Proxies -- from Neural Architecture Performance to Model Robustness

no code implementations18 Jul 2023 Jovita Lukasik, Michael Moeller, Margret Keuper

We are interested in the single prediction task for robustness and the joint multi-objective of clean and robust accuracy.

Feature Importance

Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization

1 code implementation2 Jul 2023 Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva

Using the proposed masked noise encoder to randomize style and content combinations in the training set, i. e., intra-source style augmentation (ISSA) effectively increases the diversity of training data and reduces spurious correlation.

Autonomous Driving Data Augmentation +3

Neural Architecture Design and Robustness: A Dataset

no code implementations11 Jun 2023 Steffen Jung, Jovita Lukasik, Margret Keuper

We evaluate all these networks on a range of common adversarial attacks and corruption types and introduce a database on neural architecture design and robustness evaluations.

Image Classification Neural Architecture Search

Happy People -- Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models

no code implementations11 Jun 2023 Steffen Jung, Jan Christian Schwedhelm, Claudia Schillings, Margret Keuper

In recent years, optimization in the learned latent space of deep generative models has been successfully applied to black-box optimization problems such as drug design, image generation or neural architecture search.

Image Generation Neural Architecture Search

Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters

no code implementations28 Apr 2023 Hendrik Sommerhoff, Shashank Agnihotri, Mohamed Saleh, Michael Moeller, Margret Keuper, Andreas Kolb

The success of deep learning is frequently described as the ability to train all parameters of a network on a specific application in an end-to-end fashion.

Semantic Segmentation

An Extended Study of Human-like Behavior under Adversarial Training

1 code implementation22 Mar 2023 Paul Gavrikov, Janis Keuper, Margret Keuper

Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations.

FullFormer: Generating Shapes Inside Shapes

no code implementations20 Mar 2023 Tejaswini Medi, Jawad Tayyub, Muhammad Sarmad, Frank Lindseth, Margret Keuper

Implicit generative models have been widely employed to model 3D data and have recently proven to be successful in encoding and generating high-quality 3D shapes.

3D Shape Generation Point Cloud Generation

CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks

1 code implementation4 Feb 2023 Shashank Agnihotri, Steffen Jung, Margret Keuper

Further, we set a new benchmark for adversarial attacks on optical flow, and image restoration displaying the ability to extend to any pixel-wise prediction task.

Adversarial Attack Adversarial Robustness +6

Intra-Source Style Augmentation for Improved Domain Generalization

1 code implementation18 Oct 2022 Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva

Using the proposed masked noise encoder to randomize style and content combinations in the training set, ISSA effectively increases the diversity of training data and reduces spurious correlation.

Autonomous Driving Domain Generalization +1

Robust Models are less Over-Confident

1 code implementation12 Oct 2022 Julia Grabinski, Paul Gavrikov, Janis Keuper, Margret Keuper

Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences.

Adversarial Robustness

SP-ViT: Learning 2D Spatial Priors for Vision Transformers

1 code implementation15 Jun 2022 Yuxuan Zhou, Wangmeng Xiang, Chao Li, Biao Wang, Xihan Wei, Lei Zhang, Margret Keuper, Xiansheng Hua

Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account.

Image Classification

Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks

no code implementations4 Apr 2022 Steffen Jung, Margret Keuper

The minimum cost multicut problem is the NP-hard/APX-hard combinatorial optimization problem of partitioning a real-valued edge-weighted graph such as to minimize the total cost of the partition.

Combinatorial Optimization

FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting

1 code implementation1 Apr 2022 Julia Grabinski, Steffen Jung, Janis Keuper, Margret Keuper

Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks.

Learning Where To Look -- Generative NAS is Surprisingly Efficient

1 code implementation16 Mar 2022 Jovita Lukasik, Steffen Jung, Margret Keuper

the optimization of architectures for highest classification accuracy but also in the context of hardware constraints and outperform state-of-the-art methods on several NAS benchmarks for single and multiple objectives.

Neural Architecture Search

Optimizing Edge Detection for Image Segmentation with Multicut Penalties

no code implementations10 Dec 2021 Steffen Jung, Sebastian Ziegler, Amirhossein Kardoost, Margret Keuper

The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph decomposition by optimizing binary edge labels over edge costs.

Edge Detection Image Segmentation +2

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

2 code implementations AAAI Workshop AdvML 2022 Peter Lorenz, Dominik Strassel, Margret Keuper, Janis Keuper

In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l-inf perturbations limited to eps = 8/255.

Adversarial Attack Detection Adversarial Robustness +1

Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders

1 code implementation NeurIPS 2021 Amrutha Saseendran, Kathrin Skubch, Stefan Falkner, Margret Keuper

In this paper, we propose a simple and end-to-end trainable deterministic autoencoding framework, that efficiently shapes the latent space of the model during training and utilizes the capacity of expressive multi-modal latent distributions.

Density Estimation

Aliasing coincides with CNNs vulnerability towards adversarial attacks

no code implementations AAAI Workshop AdvML 2022 Julia Grabinski, Janis Keuper, Margret Keuper

Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness.

Detecting AutoAttack Perturbations in the Frequency Domain

2 code implementations ICML Workshop AML 2021 Peter Lorenz, Paula Harder, Dominik Strassel, Margret Keuper, Janis Keuper

Recently, adversarial attacks on image classification networks by the AutoAttack (Croce and Hein, 2020b) framework have drawn a lot of attention.

Image Classification

DARTS for Inverse Problems: a Study on Stability

no code implementations NeurIPS Workshop Deep_Invers 2021 Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller

Differentiable architecture search (DARTS) is a widely researched tool for neural architecture search, due to its promising results for image classification.

Image Classification Neural Architecture Search

Is Differentiable Architecture Search truly a One-Shot Method?

no code implementations12 Aug 2021 Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller

In this work, we investigate DAS in a systematic case study of inverse problems, which allows us to analyze these potential benefits in a controlled manner.

Hyperparameter Optimization Image Classification +2

Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space

no code implementations AAAI Workshop AdvML 2022 Kalun Ho, Franz-Josef Pfreundt, Janis Keuper, Margret Keuper

Over the last decade, the development of deep image classification networks has mostly been driven by the search for the best performance in terms of classification accuracy on standardized benchmarks like ImageNet.

Clustering Image Classification

Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis

1 code implementation29 May 2021 Yang He, Ning Yu, Margret Keuper, Mario Fritz

The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes.

Colorization Denoising +2

Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation

no code implementations16 May 2021 Amirhossein Kardoost, Margret Keuper

The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking, and motion segmentation.

Motion Segmentation Multiple Object Tracking +1

SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain

3 code implementations4 Mar 2021 Paula Harder, Franz-Josef Pfreundt, Margret Keuper, Janis Keuper

Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, crafted perturbations in the input images can lead to false predictions.

Adversarial Attack

Spectral Distribution Aware Image Generation

2 code implementations5 Dec 2020 Steffen Jung, Margret Keuper

In this paper, we propose to generate images according to the frequency distribution of the real data by employing a spectral discriminator.

Image Generation

Neural Architecture Performance Prediction Using Graph Neural Networks

no code implementations19 Oct 2020 Jovita Lukasik, David Friede, Heiner Stuckenschmidt, Margret Keuper

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest.

Neural Architecture Search

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

2 code implementations9 Oct 2020 Jovita Lukasik, David Friede, Arber Zela, Frank Hutter, Margret Keuper

We evaluate the proposed approach on neural architectures defined by the ENAS approach, the NAS-Bench-101 and the NAS-Bench-201 search space and show that our smooth embedding space allows to directly extrapolate the performance prediction to architectures outside the seen domain (e. g. with more operations).

Bayesian Optimization Neural Architecture Search

Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks

1 code implementation ICLR 2022 Arber Zela, Julien Siems, Lucas Zimmer, Jovita Lukasik, Margret Keuper, Frank Hutter

We show that surrogate NAS benchmarks can model the true performance of architectures better than tabular benchmarks (at a small fraction of the cost), that they lead to faithful estimates of how well different NAS methods work on the original non-surrogate benchmark, and that they can generate new scientific insight.

Neural Architecture Search

Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches

no code implementations6 Jul 2020 Kalun Ho, Janis Keuper, Franz-Josef Pfreundt, Margret Keuper

In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings.

Clustering Image Classification +1

Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions

2 code implementations CVPR 2020 Ricard Durall, Margret Keuper, Janis Keuper

Generative convolutional deep neural networks, e. g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences.

Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts

no code implementations4 Feb 2020 Kalun Ho, Janis Keuper, Margret Keuper

Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without superivison.

Clustering Multiple Object Tracking

A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction

1 code implementation11 Dec 2019 David Friede, Jovita Lukasik, Heiner Stuckenschmidt, Margret Keuper

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest.

Neural Architecture Search

Unmasking DeepFakes with simple Features

5 code implementations2 Nov 2019 Ricard Durall, Margret Keuper, Franz-Josef Pfreundt, Janis Keuper

In this work, we present a simple way to detect such fake face images - so-called DeepFakes.

DeepFake Detection

Object Segmentation Tracking from Generic Video Cues

no code implementations5 Oct 2019 Amirhossein Kardoost, Sabine Müller, Joachim Weickert, Margret Keuper

Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning.

Object Optical Flow Estimation +4

Massively Parallel Benders Decomposition for Correlation Clustering

no code implementations15 Feb 2019 Margret Keuper, Jovita Lukasik, Maneesh Singh, Julian Yarkony

We tackle the problem of graph partitioning for image segmentation using correlation clustering (CC), which we treat as an integer linear program (ILP).

Clustering graph partitioning +2

Learning Dilation Factors for Semantic Segmentation of Street Scenes

1 code implementation6 Sep 2017 Yang He, Margret Keuper, Bernt Schiele, Mario Fritz

In this paper, we present an approach for learning dilation parameters adaptively per channel, consistently improving semantic segmentation results on street-scene datasets like Cityscapes and Camvid.

Segmentation Semantic Segmentation

ProbFlow: Joint Optical Flow and Uncertainty Estimation

no code implementations ICCV 2017 Anne S. Wannenwetsch, Margret Keuper, Stefan Roth

We overcome the artificial separation of optical flow and confidence estimation by introducing a method that jointly predicts optical flow and its underlying uncertainty.

Optical Flow Estimation Variational Inference

Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation

no code implementations ICCV 2017 Margret Keuper

Most state-of-the-art motion segmentation algorithms draw their potential from modeling motion differences of local entities such as point trajectories in terms of pairwise potentials in graphical models.

Motion Segmentation Segmentation

A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

no code implementations21 Jul 2016 Margret Keuper, Siyu Tang, Yu Zhongjie, Bjoern Andres, Thomas Brox, Bernt Schiele

Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios.

Motion Segmentation object-detection +2

Point-wise mutual information-based video segmentation with high temporal consistency

no code implementations8 Jun 2016 Margret Keuper, Thomas Brox

In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos.

Boundary Detection Optical Flow Estimation +4

Motion Trajectory Segmentation via Minimum Cost Multicuts

no code implementations ICCV 2015 Margret Keuper, Bjoern Andres, Thomas Brox

For the segmentation of moving objects in videos, the analysis of long-term point trajectories has been very popular recently.

Clustering Segmentation +1

Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation

no code implementations CVPR 2014 Fabio Galasso, Margret Keuper, Thomas Brox, Bernt Schiele

In contrast to previous work, the reduced graph is reweighted such that the resulting segmentation is equivalent, under certain assumptions, to that of the full graph.

Clustering Segmentation +3

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