1 code implementation • 20 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.
1 code implementation • 14 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.
1 code implementation • 16 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.
no code implementations • 29 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.
1 code implementation • 29 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.
1 code implementation • 21 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.
no code implementations • 25 Jul 2023 • Shashank Agnihotri, Kanchana Vaishnavi Gandikota, Julia Grabinski, Paramanand Chandramouli, Margret Keuper
We consider the recently proposed Restormer model, as well as NAFNet and the "Baseline network" which are both simplified versions of a Restormer.
1 code implementation • 20 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.
no code implementations • 19 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.
no code implementations • 19 Jul 2023 • Julia Grabinski, Janis Keuper, Margret Keuper
Motivated by the recent trend towards the usage of larger receptive fields for more context-aware neural networks in vision applications, we aim to investigate how large these receptive fields really need to be.
no code implementations • 18 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.
1 code implementation • 2 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.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 28 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.
1 code implementation • 22 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.
no code implementations • 20 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.
1 code implementation • 4 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.
1 code implementation • 13 Dec 2022 • Peter Lorenz, Margret Keuper, Janis Keuper
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks.
1 code implementation • 17 Nov 2022 • Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yanwen Fang, Yifeng Geng, Xuansong Xie, Margret Keuper
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections.
Ranked #7 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • 18 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.
1 code implementation • 12 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.
1 code implementation • 15 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.
Ranked #153 on Image Classification on ImageNet
no code implementations • 4 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.
1 code implementation • 1 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.
1 code implementation • 16 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.
no code implementations • 10 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.
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.
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.
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.
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.
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.
no code implementations • 12 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.
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.
1 code implementation • 29 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.
no code implementations • 16 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.
1 code implementation • ICCV 2021 • Amrutha Saseendran, Kathrin Skubch, Margret Keuper
Image generation has rapidly evolved in recent years.
3 code implementations • 4 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.
2 code implementations • 5 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.
no code implementations • 19 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.
2 code implementations • 9 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).
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.
no code implementations • 18 Aug 2020 • Amirhossein Kardoost, Kalun Ho, Peter Ochs, Margret Keuper
We evaluate our method on the well-known motion segmentation datasets FBMS59 and DAVIS16.
no code implementations • 6 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.
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.
no code implementations • 4 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.
1 code implementation • 11 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.
5 code implementations • 2 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.
no code implementations • 5 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.
no code implementations • 15 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).
1 code implementation • ECCV 2018 • Eddy Ilg, Tonmoy Saikia, Margret Keuper, Thomas Brox
Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
1 code implementation • 6 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.
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.
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.
12 code implementations • CVPR 2017 • Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, Thomas Brox
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
Dense Pixel Correspondence Estimation Optical Flow Estimation +1
no code implementations • 21 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.
no code implementations • 8 Jun 2016 • Margret Keuper, Thomas Brox
In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos.
1 code implementation • CVPR 2017 • Yang He, Wei-Chen Chiu, Margret Keuper, Mario Fritz
The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene.
Ranked #96 on Semantic Segmentation on NYU Depth v2
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.
no code implementations • ICCV 2015 • Margret Keuper, Evgeny Levinkov, Nicolas Bonneel, Guillaume Lavoué, Thomas Brox, Bjoern Andres
a pixel grid graph have received little attention, firstly, because the MP is NP-hard and instances w. r. t.
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.
no code implementations • CVPR 2013 • Margret Keuper, Thorsten Schmidt, Maja Temerinac-Ott, Jan Padeken, Patrick Heun, Olaf Ronneberger, Thomas Brox
With volumetric data from widefield fluorescence microscopy, many emerging questions in biological and biomedical research are being investigated.