Search Results for author: Stefan Roth

Found 74 papers, 35 papers with code

Enhancing the Secrecy Rate with Direction-range Focusing with FDA and RIS

no code implementations26 Jan 2024 Chu Li, Stefan Roth, Aydin Sezgin

Simulations verify the correctness of the closed-form expressions and demonstrate that we can effectively improve the secrecy rate, especially when the eavesdropper is close to the RIS or the legitimate user.

Pixel State Value Network for Combined Prediction and Planning in Interactive Environments

no code implementations11 Oct 2023 Sascha Rosbach, Stefan M. Leupold, Simon Großjohann, Stefan Roth

Automated vehicles operating in urban environments have to reliably interact with other traffic participants.

Vision Relation Transformer for Unbiased Scene Graph Generation

1 code implementation ICCV 2023 Gopika Sudhakaran, Devendra Singh Dhami, Kristian Kersting, Stefan Roth

Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on top of an object encoder-decoder backbone.

Graph Generation Relation +2

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

1 code implementation ICCV 2023 Robin Hesse, Simone Schaub-Meyer, Stefan Roth

Using our tools, we report results for 24 different combinations of neural models and XAI methods, demonstrating the strengths and weaknesses of the assessed methods in a fully automatic and systematic manner.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Content-Adaptive Downsampling in Convolutional Neural Networks

1 code implementation16 May 2023 Robin Hesse, Simone Schaub-Meyer, Stefan Roth

Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost.

Efficient Feature Extraction for High-resolution Video Frame Interpolation

1 code implementation25 Nov 2022 Moritz Nottebaum, Stefan Roth, Simone Schaub-Meyer

The feature extraction layers help to compress the input and extract relevant information for the latter stages, such as motion estimation.

Dimensionality Reduction Image Generation +3

$S^2$-Flow: Joint Semantic and Style Editing of Facial Images

1 code implementation22 Nov 2022 Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth

In addition, methods that use semantic masks to edit images have difficulty preserving the identity and are unable to perform controlled style edits.

Diverse Image Captioning with Grounded Style

1 code implementation3 May 2022 Franz Klein, Shweta Mahajan, Stefan Roth

Stylized image captioning as presented in prior work aims to generate captions that reflect characteristics beyond a factual description of the scene composition, such as sentiments.

Attribute Image Captioning

Fast Axiomatic Attribution for Neural Networks

1 code implementation NeurIPS 2021 Robin Hesse, Simone Schaub-Meyer, Stefan Roth

Mitigating the dependence on spurious correlations present in the training dataset is a quickly emerging and important topic of deep learning.

Dense Unsupervised Learning for Video Segmentation

1 code implementation NeurIPS 2021 Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth

On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.

Segmentation Semantic Segmentation +4

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

1 code implementation ICCV 2021 Shweta Mahajan, Stefan Roth

Autoregressive models are a class of exact inference approaches with highly flexible functional forms, yielding state-of-the-art density estimates for natural images.

Density Estimation

Noise-Contrastive Variational Information Bottleneck Networks

no code implementations29 Sep 2021 Jannik Schmitt, Stefan Roth

While deep neural networks for classification have shown impressive predictive performance, e. g. in image classification, they generally tend to be overconfident.

Classification Image Classification

Adaptive Generalization for Semantic Segmentation

no code implementations29 Sep 2021 Sherwin Bahmani, Oliver Hahn, Eduard Sebastian Zamfir, Nikita Araslanov, Stefan Roth

In this work, we empirically study an adaptive inference strategy for semantic segmentation that adjusts the model to the test sample before producing the final prediction.

Segmentation Semantic Segmentation +1

TxT: Crossmodal End-to-End Learning with Transformers

no code implementations9 Sep 2021 Jan-Martin O. Steitz, Jonas Pfeiffer, Iryna Gurevych, Stefan Roth

Reasoning over multiple modalities, e. g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains.

Multimodal Reasoning Question Answering +1

Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring

no code implementations CVPR 2021 Jiangxin Dong, Stefan Roth, Bernt Schiele

The classical maximum a-posteriori (MAP) framework for non-blind image deblurring requires defining suitable data and regularization terms, whose interplay yields the desired clear image through optimization.

Blind Image Deblurring Image Deblurring

Self-Supervised Multi-Frame Monocular Scene Flow

1 code implementation CVPR 2021 Junhwa Hur, Stefan Roth

Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup.

Scene Flow Estimation Self-Supervised Learning

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

1 code implementation NeurIPS 2020 Jiangxin Dong, Stefan Roth, Bernt Schiele

We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning.

Blind Image Deblurring Image Deblurring

Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise

no code implementations15 Mar 2021 Jannik Schmitt, Stefan Roth

Variational inference methods for BNNs approximate the intractable weight posterior with a tractable distribution, yet mostly rely on sampling from the variational distribution during training and inference.

Image Classification Variational Inference

Localization Attack by Precoder Feedback Overhearing in 5G Networks and Countermeasures

no code implementations14 Dec 2020 Stefan Roth, Stefano Tomasin, Marco Maso, Aydin Sezgin

We analyze the attack and assess the obtained localization accuracy against various parameters.

Information Theory Cryptography and Security Signal Processing Information Theory

Diverse Image Captioning with Context-Object Split Latent Spaces

1 code implementation NeurIPS 2020 Shweta Mahajan, Stefan Roth

Our framework not only enables diverse captioning through context-based pseudo supervision, but extends this to images with novel objects and without paired captions in the training data.

Image Captioning Object

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

no code implementations15 Oct 2020 Patrick Dendorfer, Aljoša Ošep, Anton Milan, Konrad Schindler, Daniel Cremers, Ian Reid, Stefan Roth, Laura Leal-Taixé

We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods.

Multiple Object Tracking Multiple People Tracking +3

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery

no code implementations28 May 2020 Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation.

object-detection Object Detection +1

Single-Stage Semantic Segmentation from Image Labels

1 code implementation CVPR 2020 Nikita Araslanov, Stefan Roth

This is in contrast to earlier work that used only a single stage $-$ training one segmentation network on image labels $-$ which was abandoned due to inferior segmentation accuracy.

Segmentation Semantic Segmentation

Self-Supervised Monocular Scene Flow Estimation

1 code implementation CVPR 2020 Junhwa Hur, Stefan Roth

Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks.

Monocular Depth Estimation Optical Flow Estimation +2

Normalizing Flows with Multi-Scale Autoregressive Priors

1 code implementation CVPR 2020 Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz, Bernt Schiele, Stefan Roth

Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis.

Density Estimation Image Generation

Optical Flow Estimation in the Deep Learning Age

no code implementations6 Apr 2020 Junhwa Hur, Stefan Roth

Akin to many subareas of computer vision, the recent advances in deep learning have also significantly influenced the literature on optical flow.

Motion Estimation Optical Flow Estimation

MOT20: A benchmark for multi object tracking in crowded scenes

1 code implementation19 Mar 2020 Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixé

The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.

Multi-Object Tracking Multiple Object Tracking with Transformer +2

Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings

1 code implementation ICLR 2020 Shweta Mahajan, Iryna Gurevych, Stefan Roth

Therefore, we propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately.

Image Captioning Image Generation

Deep Video Deblurring: The Devil is in the Details

1 code implementation26 Sep 2019 Jochen Gast, Stefan Roth

In contrast to these involved models, we found that a simple baseline CNN can perform astonishingly well when particular care is taken w. r. t.

Deblurring

Markov Decision Process for Video Generation

no code implementations26 Sep 2019 Vladyslav Yushchenko, Nikita Araslanov, Stefan Roth

We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping.

Video Generation

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings

no code implementations14 Sep 2019 Shweta Mahajan, Teresa Botschen, Iryna Gurevych, Stefan Roth

One of the key challenges in learning joint embeddings of multiple modalities, e. g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets.

Cross-Modal Retrieval Retrieval

Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice

1 code implementation9 Sep 2019 Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler, Stefan Roth

When adding our network layer to state-of-the-art networks for optical flow and semantic segmentation, boundary artifacts are removed and the accuracy is improved.

Optical Flow Estimation Semantic Segmentation

Actor-Critic Instance Segmentation

1 code implementation CVPR 2019 Nikita Araslanov, Constantin Rothkopf, Stefan Roth

Most approaches to visual scene analysis have emphasised parallel processing of the image elements.

Instance Segmentation Segmentation +1

Neural Nearest Neighbors Networks

2 code implementations NeurIPS 2018 Tobias Plötz, Stefan Roth

To exploit our relaxation, we propose the neural nearest neighbors block (N3 block), a novel non-local processing layer that leverages the principle of self-similarity and can be used as building block in modern neural network architectures.

Image Denoising Image Restoration +1

Multi-view X-ray R-CNN

no code implementations4 Oct 2018 Jan-Martin O. Steitz, Faraz Saeedan, Stefan Roth

First, we introduce a novel multi-view pooling layer to perform a 3D aggregation of 2D CNN-features extracted from each view.

General Classification object-detection +1

Normalized Blind Deconvolution

no code implementations ECCV 2018 Meiguang Jin, Stefan Roth, Paolo Favaro

We introduce a family of novel approaches to single-image blind deconvolution, ie , the problem of recovering a sharp image and a blur kernel from a single blurry input.

A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning

no code implementations SEMEVAL 2018 Hatem Mousselly-Sergieh, Teresa Botschen, Iryna Gurevych, Stefan Roth

Current methods for knowledge graph (KG) representation learning focus solely on the structure of the KG and do not exploit any kind of external information, such as visual and linguistic information corresponding to the KG entities.

Graph Representation Learning Information Retrieval +3

Lightweight Probabilistic Deep Networks

4 code implementations CVPR 2018 Jochen Gast, Stefan Roth

Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice.

Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers

3 code implementations CVPR 2018 Stephan R. Richter, Stefan Roth

We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.

3D Object Reconstruction 3D Shape Reconstruction

Detail-Preserving Pooling in Deep Networks

2 code implementations CVPR 2018 Faraz Saeedan, Nicolas Weber, Michael Goesele, Stefan Roth

This is commonly referred to as pooling, and is applied to reduce the number of parameters, improve invariance to certain distortions, and increase the receptive field size.

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

2 code implementations21 Nov 2017 Simon Meister, Junhwa Hur, Stefan Roth

By optionally fine-tuning on the KITTI training data, our method achieves competitive optical flow accuracy on the KITTI 2012 and 2015 benchmarks, thus in addition enabling generic pre-training of supervised networks for datasets with limited amounts of ground truth.

Optical Flow Estimation Test

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

MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation

no code implementations ICCV 2017 Junhwa Hur, Stefan Roth

The key feature of our model is to fully exploit the symmetry properties that characterize optical flow and occlusions in the two consecutive images.

Occlusion Estimation Optical Flow Estimation

Benchmarking Denoising Algorithms with Real Photographs

no code implementations CVPR 2017 Tobias Plötz, Stefan Roth

Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i. i. d.

Benchmarking Image Denoising

Robust Multi-Image HDR Reconstruction for the Modulo Camera

no code implementations5 Jul 2017 Florian Lang, Tobias Plötz, Stefan Roth

While the concept is appealing, we show that the original reconstruction approach assumes noise-free measurements and quickly breaks down otherwise.

HDR Reconstruction

Noise-Blind Image Deblurring

no code implementations CVPR 2017 Meiguang Jin, Stefan Roth, Paolo Favaro

We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level.

Blind Image Deblurring Computational Efficiency +1

The Stixel world: A medium-level representation of traffic scenes

no code implementations2 Apr 2017 Marius Cordts, Timo Rehfeld, Lukas Schneider, David Pfeiffer, Markus Enzweiler, Stefan Roth, Marc Pollefeys, Uwe Franke

We believe this challenge should be faced by introducing a representation of the sensory data that provides compressed and structured access to all relevant visual content of the scene.

Autonomous Vehicles object-detection +1

Playing for Data: Ground Truth from Computer Games

2 code implementations7 Aug 2016 Stephan R. Richter, Vibhav Vineet, Stefan Roth, Vladlen Koltun

Recent progress in computer vision has been driven by high-capacity models trained on large datasets.

Semantic Segmentation

Stereo Video Deblurring

no code implementations28 Jul 2016 Anita Sellent, Carsten Rother, Stefan Roth

With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task.

Deblurring

Joint Optical Flow and Temporally Consistent Semantic Segmentation

no code implementations26 Jul 2016 Junhwa Hur, Stefan Roth

The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems.

Motion Estimation Optical Flow Estimation +3

Parametric Object Motion from Blur

no code implementations CVPR 2016 Jochen Gast, Anita Sellent, Stefan Roth

A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone.

Deblurring Motion Segmentation +3

MOT16: A Benchmark for Multi-Object Tracking

8 code implementations2 Mar 2016 Anton Milan, Laura Leal-Taixe, Ian Reid, Stefan Roth, Konrad Schindler

Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.

Multi-Object Tracking Multiple Object Tracking +2

Registering Images to Untextured Geometry Using Average Shading Gradients

no code implementations ICCV 2015 Tobias Plotz, Stefan Roth

Many existing approaches for image-to-geometry registration assume that either a textured 3D model or a good initial guess of the 3D pose is available to bootstrap the registration process.

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

2 code implementations8 Apr 2015 Laura Leal-Taixé, Anton Milan, Ian Reid, Stefan Roth, Konrad Schindler

We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system.

3D Reconstruction Multiple Object Tracking +3

Shrinkage Fields for Effective Image Restoration

no code implementations CVPR 2014 Uwe Schmidt, Stefan Roth

To that end we propose shrinkage fields, a random field-based architecture that combines the image model and the optimization algorithm in a single unit.

Computational Efficiency Image Restoration

Cascades of Regression Tree Fields for Image Restoration

no code implementations8 Apr 2014 Uwe Schmidt, Jeremy Jancsary, Sebastian Nowozin, Stefan Roth, Carsten Rother

We posit two reasons for this: First, the blur kernel is often only known at test time, requiring any discriminative approach to cope with considerable variability.

Blind Image Deblurring Image Deblurring +4

Detection- and Trajectory-Level Exclusion in Multiple Object Tracking

no code implementations CVPR 2013 Anton Milan, Konrad Schindler, Stefan Roth

When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be assigned at most one observation per frame; (2) in trajectory estimation, two trajectories should remain spatially separated at all times to avoid collisions.

Multiple Object Tracking Object

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