Search Results for author:
Found 53 papers, 33 papers with code
Multi-conditioned Graph Diffusion for Neural Architecture Search
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
Pedestrian Environment Model for Automated Driving
We only use images from a monocular camera and the vehicle's localization data as input to our pedestrian environment model.
Out-of-Distribution Detection for Monocular Depth Estimation
In monocular depth estimation, uncertainty estimation approaches mainly target the data uncertainty introduced by image noise.
SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
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.
Automated Automotive Radar Calibration With Intelligent Vehicles
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.
Data-Free Backbone Fine-Tuning for Pruned Neural Networks
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.
Automated Static Camera Calibration with Intelligent Vehicles
Our method does not require any human interaction with the information recorded by both the infrastructure and the vehicle.
RESET: Revisiting Trajectory Sets for Conditional Behavior Prediction
It is desirable to predict the behavior of traffic participants conditioned on different planned trajectories of the autonomous vehicle.
Localizing Spatial Information in Neural Spatiospectral Filters
Beamforming for multichannel speech enhancement relies on the estimation of spatial characteristics of the acoustic scene.
Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic.
Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs
In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations.
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
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)
Knowing What to Label for Few Shot Microscopy Image Cell Segmentation
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.
Heatmap-based Out-of-Distribution Detection
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.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Extrinsic Camera Calibration with Semantic Segmentation
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.
Gradient-based Uncertainty for Monocular Depth Estimation
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.
Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation
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.
MotionMixer: MLP-based 3D Human Body Pose Forecasting
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
A Spatio-Temporal Multilayer Perceptron for Gesture Recognition
Gesture recognition is essential for the interaction of autonomous vehicles with humans.
Ranked #1 on
Skeleton Based Action Recognition
on Drive&Act
Translation Consistent Semi-supervised Segmentation for 3D Medical Images
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.
Lightweight Monocular Depth Estimation through Guided Decoding
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.
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification
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).
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
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.
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
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
Anomaly Detection in Multi-Agent Trajectories for Automated Driving
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.
Learning Temporal 3D Human Pose Estimation with Pseudo-Labels
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
MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation
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.
Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
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
Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
We select the task of monocular depth estimation where our goal is to transform a pre-trained model to the target's domain data.
Attention-based Vehicle Self-Localization with HD Feature Maps
We present a vehicle self-localization method using point-based deep neural networks.
ParticleAugment: Sampling-Based Data Augmentation
By comparing with the related work, our method reaches a balance between the computational cost of policy search and the model performance.
ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
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
NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification
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
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
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
Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
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.
EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels
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.
Point Transformer
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
Multiple Trajectory Prediction with Deep Temporal and Spatial Convolutional Neural Networks
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.
Traffic Control Gesture Recognition for Autonomous Vehicles
A car driver knows how to react on the gestures of the traffic officers.
Ranked #1 on
Skeleton Based Action Recognition
on TCG-dataset
DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration
This work addresses the problem of point cloud registration using deep neural networks.
Few-Shot Microscopy Image Cell Segmentation
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.
LACI: Low-effort Automatic Calibration of Infrastructure Sensors
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.
Few-Shot Meta-Denoising
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.
DeepLocalization: Landmark-based Self-Localization with Deep Neural Networks
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.
Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets
In this work, we explore the correlation between people trajectories and their head orientations.
Adversarial Signal Denoising with Encoder-Decoder Networks
The presence of noise is common in signal processing regardless the signal type.
Adversarial Network Compression
Neural network compression has recently received much attention due to the computational requirements of modern deep models.
3D Pictorial Structures Revisited: Multiple Human Pose Estimation
We address the problem of 3D pose estimation of multiple humans from multiple views.
Ranked #15 on
3D Multi-Person Pose Estimation
on Campus
Deeper Depth Prediction with Fully Convolutional Residual Networks
This paper addresses the problem of estimating the depth map of a scene given a single RGB image.
Recurrent Human Pose Estimation
We propose a novel ConvNet model for predicting 2D human body poses in an image.
Robust Optimization for Deep Regression
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.
Multiple human pose estimation with temporally consistent 3d pictorial structures
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
3D Pictorial Structures for Multiple Human Pose Estimation
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
