1 code implementation • 9 Mar 2024 • Rohan Asthana, Joschua Conrad, Youssef Dawoud, Maurits Ortmanns, Vasileios Belagiannis
To advance the architecture search, we present a graph diffusion-based NAS approach that uses discrete conditional graph diffusion processes to generate high-performing neural network architectures.
Ranked #1 on Neural Architecture Search on NAS-Bench-301
1 code implementation • 17 Aug 2023 • Adrian Holzbock, Alexander Tsaregorodtsev, Vasileios Belagiannis
We only use images from a monocular camera and the vehicle's localization data as input to our pedestrian environment model.
1 code implementation • ICCV 2023 • Julia Hornauer, Adrian Holzbock, Vasileios Belagiannis
In monocular depth estimation, uncertainty estimation approaches mainly target the data uncertainty introduced by image noise.
1 code implementation • 9 Aug 2023 • Youssef Dawoud, Gustavo Carneiro, Vasileios Belagiannis
Few-shot domain adaptation mitigates this issue by adapting deep neural networks pre-trained on the source domain to the target domain using a randomly selected and annotated support set from the target domain.
no code implementations • 23 Jun 2023 • Alexander Tsaregorodtsev, Michael Buchholz, Vasileios Belagiannis
We, therefore, present an approach for automated and geo-referenced extrinsic calibration of automotive radar sensors that is based on a novel hypothesis filtering scheme.
1 code implementation • 22 Jun 2023 • Adrian Holzbock, Achyut Hegde, Klaus Dietmayer, Vasileios Belagiannis
In particular, the pruned network backbone is trained with synthetically generated images, and our proposed intermediate supervision to mimic the unpruned backbone's output feature map.
1 code implementation • 21 Apr 2023 • Alexander Tsaregorodtsev, Adrian Holzbock, Jan Strohbeck, Michael Buchholz, Vasileios Belagiannis
Our method does not require any human interaction with the information recorded by both the infrastructure and the vehicle.
no code implementations • 12 Apr 2023 • Julian Schmidt, Pascal Huissel, Julian Wiederer, Julian Jordan, Vasileios Belagiannis, Klaus Dietmayer
It is desirable to predict the behavior of traffic participants conditioned on different planned trajectories of the autonomous vehicle.
no code implementations • 14 Mar 2023 • Annika Briegleb, Thomas Haubner, Vasileios Belagiannis, Walter Kellermann
Beamforming for multichannel speech enhancement relies on the estimation of spatial characteristics of the acoustic scene.
no code implementations • 20 Feb 2023 • Adrian Holzbock, Nicolai Kern, Christian Waldschmidt, Klaus Dietmayer, Vasileios Belagiannis
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic.
no code implementations • 6 Dec 2022 • Osman Ülger, Julian Wiederer, Mohsen Ghafoorian, Vasileios Belagiannis, Pascal Mettes
In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations.
1 code implementation • ICCV 2023 • Yuyuan Liu, Choubo Ding, Yu Tian, Guansong Pang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes.
Ranked #1 on Anomaly Detection on Fishyscapes (using extra training data)
1 code implementation • 18 Nov 2022 • Youssef Dawoud, Arij Bouazizi, Katharina Ernst, Gustavo Carneiro, Vasileios Belagiannis
In this paper, we argue that the random selection of unlabelled training target images to be annotated and included in the support set may not enable an effective fine-tuning process, so we propose a new approach to optimise this image selection process.
1 code implementation • 15 Nov 2022 • Julia Hornauer, Vasileios Belagiannis
Given a trained and fixed classifier, we train a decoder neural network to produce heatmaps with zero response for in-distribution samples and high response heatmaps for OOD samples, based on the classifier features and the class prediction.
1 code implementation • 8 Aug 2022 • Alexander Tsaregorodtsev, Johannes Müller, Jan Strohbeck, Martin Herrmann, Michael Buchholz, Vasileios Belagiannis
Our approach relies on a coarse initial measurement of the camera pose and builds on lidar sensors mounted on a vehicle with high-precision localization to capture a point cloud of the camera environment.
no code implementations • 3 Aug 2022 • Youssef Dawoud, Katharina Ernst, Gustavo Carneiro, Vasileios Belagiannis
Deep neural networks currently deliver promising results for microscopy image cell segmentation, but they require large-scale labelled databases, which is a costly and time-consuming process.
1 code implementation • 3 Aug 2022 • Julia Hornauer, Vasileios Belagiannis
To avoid relying on ground-truth information for the loss definition, we present an auxiliary loss function based on the correspondence of the depth prediction for an image and its horizontally flipped counterpart.
1 code implementation • 1 Jul 2022 • Arij Bouazizi, Adrian Holzbock, Ulrich Kressel, Klaus Dietmayer, Vasileios Belagiannis
Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints.
Ranked #6 on Human Pose Forecasting on Human3.6M
1 code implementation • 25 Apr 2022 • Adrian Holzbock, Alexander Tsaregorodtsev, Youssef Dawoud, Klaus Dietmayer, Vasileios Belagiannis
Gesture recognition is essential for the interaction of autonomous vehicles with humans.
Ranked #1 on Skeleton Based Action Recognition on Drive&Act
1 code implementation • 28 Mar 2022 • Yuyuan Liu, Yu Tian, Chong Wang, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, Gustavo Carneiro
The most successful SSL approaches are based on consistency learning that minimises the distance between model responses obtained from perturbed views of the unlabelled data.
1 code implementation • 8 Mar 2022 • Michael Rudolph, Youssef Dawoud, Ronja Güldenring, Lazaros Nalpantidis, Vasileios Belagiannis
Similarly, on the KITTI dataset, inference is possible with up to 23. 7 fps on the Jetson Nano and 102. 9 fps on the Xavier NX.
1 code implementation • CVPR 2022 • Yuyuan Liu, Yu Tian, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, Gustavo Carneiro
The accurate prediction by this model allows us to use a challenging combination of network, input data and feature perturbations to improve the consistency learning generalisation, where the feature perturbations consist of a new adversarial perturbation.
1 code implementation • CVPR 2022 • Fengbei Liu, Yu Tian, Yuanhong Chen, Yuyuan Liu, Vasileios Belagiannis, Gustavo Carneiro
Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e. g., lesion classification) and multi-label (e. g., multiple-disease diagnosis) problems, and 2) handle imbalanced learning (because of the high variance in disease prevalence).
1 code implementation • 22 Oct 2021 • Filipe R. Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and "MixMatched" with the clean samples.
Ranked #1 on Image Classification with Label Noise on CIFAR-100
Image Classification with Label Noise Learning with noisy labels
1 code implementation • 15 Oct 2021 • Julian Wiederer, Arij Bouazizi, Marco Troina, Ulrich Kressel, Vasileios Belagiannis
Due to the lack of multi-agent trajectory datasets for anomaly detection in automated driving, we introduce our dataset using a driving simulator for normal and abnormal manoeuvres.
2 code implementations • 14 Oct 2021 • Arij Bouazizi, Ulrich Kressel, Vasileios Belagiannis
We present a simple, yet effective, approach for self-supervised 3D human pose estimation.
Ranked #49 on 3D Human Pose Estimation on MPI-INF-3DHP
no code implementations • 18 Sep 2021 • Anastasia Makarevich, Azade Farshad, Vasileios Belagiannis, Nassir Navab
In this work, we present MetaMedSeg, a gradient-based meta-learning algorithm that redefines the meta-learning task for the volumetric medical data with the goal to capture the variety between the slices.
1 code implementation • 17 Aug 2021 • Arij Bouazizi, Julian Wiederer, Ulrich Kressel, Vasileios Belagiannis
We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view.
Ranked #12 on Weakly-supervised 3D Human Pose Estimation on Human3.6M
Self-Supervised Learning Weakly-supervised 3D Human Pose Estimation +1
1 code implementation • 5 Aug 2021 • Julia Hornauer, Lazaros Nalpantidis, Vasileios Belagiannis
We select the task of monocular depth estimation where our goal is to transform a pre-trained model to the target's domain data.
no code implementations • 16 Jul 2021 • Nico Engel, Vasileios Belagiannis, Klaus Dietmayer
We present a vehicle self-localization method using point-based deep neural networks.
no code implementations • 16 Jun 2021 • Alexander Tsaregorodtsev, Vasileios Belagiannis
By comparing with the related work, our method reaches a balance between the computational cost of policy search and the model performance.
1 code implementation • 21 Mar 2021 • Ragav Sachdeva, Filipe R Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods.
Ranked #24 on Image Classification on mini WebVision 1.0
1 code implementation • 6 Mar 2021 • Fengbei Liu, Yuanhong Chen, Yu Tian, Yuyuan Liu, Chong Wang, Vasileios Belagiannis, Gustavo Carneiro
In this paper, we propose a new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem.
Image Classification with Label Noise Learning with noisy labels +1
1 code implementation • 6 Mar 2021 • Filipe R. Cordeiro, Ragav Sachdeva, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue.
Ranked #4 on Image Classification on Food-101N
1 code implementation • 5 Mar 2021 • Fengbei Liu, Yu Tian, Filipe R. Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
In this paper, we propose Self-supervised Mean Teacher for Semi-supervised (S$^2$MTS$^2$) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning.
1 code implementation • 11 Nov 2020 • Ragav Sachdeva, Filipe R. Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
In this work, we study a new variant of the noisy label problem that combines the open-set and closed-set noisy labels, and introduce a benchmark evaluation to assess the performance of training algorithms under this setup.
2 code implementations • 2 Nov 2020 • Nico Engel, Vasileios Belagiannis, Klaus Dietmayer
In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets.
Ranked #35 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 29 Oct 2020 • Jan Strohbeck, Vasileios Belagiannis, Johannes Muller, Marcel Schreiber, Martin Herrmann, Daniel Wolf and Michael Buchholz
Automated vehicles need to not only perceive their environment, but also predict the possible future behavior of all detected traffic participants in order to safely navigate in complex scenarios and avoid critical situations, ranging from merging on highways to crossing urban intersections.
1 code implementation • 31 Jul 2020 • Julian Wiederer, Arij Bouazizi, Ulrich Kressel, Vasileios Belagiannis
A car driver knows how to react on the gestures of the traffic officers.
Ranked #1 on Skeleton Based Action Recognition on TCG-dataset
1 code implementation • 22 Jul 2020 • Markus Horn, Nico Engel, Vasileios Belagiannis, Michael Buchholz, Klaus Dietmayer
This work addresses the problem of point cloud registration using deep neural networks.
1 code implementation • 29 Jun 2020 • Youssef Dawoud, Julia Hornauer, Gustavo Carneiro, Vasileios Belagiannis
Instead, we assume that we can access a plethora of annotated image data sets from different domains (sources) and a limited number of annotated image data sets from the domain of interest (target), where each domain denotes not only different image appearance but also a different type of cell segmentation problem.
no code implementations • 5 Nov 2019 • Johannes Müller, Martin Herrmann, Jan Strohbeck, Vasileios Belagiannis, Michael Buchholz
While classical approaches are sensor-specific and often need calibration targets as well as a widely overlapping field of view (FOV), within this work, a cooperative intelligent vehicle is used as callibration target.
no code implementations • 31 Jul 2019 • Leslie Casas, Attila Klimmek, Gustavo Carneiro, Nassir Navab, Vasileios Belagiannis
A solution to mitigate the small training set issue is to pre-train a denoising model with small training sets containing pairs of clean and synthesized noisy signals, produced from empirical noise priors, and fine-tune on the available small training set.
no code implementations • 18 Apr 2019 • Nico Engel, Stefan Hoermann, Markus Horn, Vasileios Belagiannis, Klaus Dietmayer
The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected similarly on the fly.
no code implementations • 7 Jan 2019 • Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, Fabio Galasso
In this work, we explore the correlation between people trajectories and their head orientations.
no code implementations • 20 Dec 2018 • Leslie Casas, Attila Klimmek, Nassir Navab, Vasileios Belagiannis
The presence of noise is common in signal processing regardless the signal type.
no code implementations • 28 Mar 2018 • Vasileios Belagiannis, Azade Farshad, Fabio Galasso
Neural network compression has recently received much attention due to the computational requirements of modern deep models.
no code implementations • 1 Oct 2016 • Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, Slobodan Ilic
We address the problem of 3D pose estimation of multiple humans from multiple views.
Ranked #15 on 3D Multi-Person Pose Estimation on Campus
18 code implementations • 1 Jun 2016 • Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
This paper addresses the problem of estimating the depth map of a scene given a single RGB image.
no code implementations • 10 May 2016 • Vasileios Belagiannis, Andrew Zisserman
We propose a novel ConvNet model for predicting 2D human body poses in an image.
1 code implementation • ICCV 2015 • Vasileios Belagiannis, Christian Rupprecht, Gustavo Carneiro, Nassir Navab
Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection.
no code implementations • 6 Sep 2014 • Vasileios Belagiannis, Xinchao Wang, Bernt Schiele, Pascal Fua, Slobodan Ilic, Nassir Navab
To address these challenges, we propose a temporally consistent 3D Pictorial Structures model (3DPS) for multiple human pose estimation from multiple camera views.
Ranked #16 on 3D Multi-Person Pose Estimation on Campus
no code implementations • CVPR 2014 • Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, Slobodan Ilic
In this work, we address the problem of 3D pose estimation of multiple humans from multiple views.
Ranked #24 on 3D Multi-Person Pose Estimation on Shelf