Search Results for author:
Found 64 papers, 35 papers with code
Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap
Specifically, we evaluate object detectors and an online mapping model on real and simulated data, and study the effects of different fine-tuning strategies. Our results show notable improvements in model robustness to simulated data, even improving real-world performance in some cases.
ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation
We implement ECAP on top of the recent method MIC and boost its performance on two synthetic-to-real domain adaptation benchmarks.
On the connection between Noise-Contrastive Estimation and Contrastive Divergence
Noise-contrastive estimation (NCE) is a popular method for estimating unnormalised probabilistic models, such as energy-based models, which are effective for modelling complex data distributions.
Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
Multi-object tracking (MOT) is the task of estimating the state trajectories of an unknown and time-varying number of objects over a certain time window.
Markov Chain Monte Carlo Data Association for Sets of Trajectories
This paper considers a batch solution to the multi-object tracking problem based on sets of trajectories.
NeuRAD: Neural Rendering for Autonomous Driving
Neural radiance fields (NeRFs) have gained popularity in the autonomous driving (AD) community.
Graph GOSPA metric: a metric to measure the discrepancy between graphs of different sizes
This paper proposes a metric to measure the dissimilarity between graphs that may have a different number of nodes.
You can have your ensemble and run it too -- Deep Ensembles Spread Over Time
We find that DESOT obtains the benefits of deep ensembles, in terms of predictive and uncertainty estimation performance, while avoiding the added computational cost.
Integrated Monostatic and Bistatic mmWave Sensing
Millimeter-wave (mmWave) signals provide attractive opportunities for sensing due to their inherent geometrical connections to physical propagation channels.
MCMC-Correction of Score-Based Diffusion Models for Model Composition
Diffusion models can be parameterised in terms of either a score or an energy function.
Set-Type Belief Propagation with Applications to Poisson Multi-Bernoulli SLAM
In this paper, we develop BP rules for factor graphs defined on sequences of RFSs where each RFS has an unknown number of elements, with the intention of deriving novel inference methods for RFSs.
Simultaneous Localization and Mapping
Vocal Bursts Type Prediction
Experimental Validation of Single BS 5G mmWave Positioning and Mapping for Intelligent Transport
Positioning with 5G signals generally requires connection to several base stations (BSs), which makes positioning more demanding in terms of infrastructure than communications.
Improving Open-Set Semi-Supervised Learning with Self-Supervision
Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set.
LidarCLIP or: How I Learned to Talk to Point Clouds
We also explore zero-shot classification and show that LidarCLIP outperforms existing attempts to use CLIP for point clouds by a large margin.
MmWave Mapping and SLAM for 5G and Beyond
We distinguish the different types of sensing problems and then focus on mapping and SLAM as running examples.
Deep Fusion of Multi-Object Densities Using Transformer
We compare the performance of the transformer-based fusion method with a well-performing model-based Bayesian fusion method in several simulated scenarios with different parameter settings using synthetic data.
Doppler Exploitation in Bistatic mmWave Radio SLAM
Networks in 5G and beyond utilize millimeter wave (mmWave) radio signals, large bandwidths, and large antenna arrays, which bring opportunities in jointly localizing the user equipment and mapping the propagation environment, termed as simultaneous localization and mapping (SLAM).
Trajectory PMB Filters for Extended Object Tracking Using Belief Propagation
First, we present a PMBM conjugate prior on the posterior of sets of trajectories for a generalized measurement model, in which each object generates an independent set of measurements.
A comparison between PMBM Bayesian track initiation and labelled RFS adaptive birth
This paper provides a comparative analysis between the adaptive birth model used in the labelled random finite set literature and the track initiation in the Poisson multi-Bernoulli mixture (PMBM) filter, with point-target models.
Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds
Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds.
Multiple Object Trajectory Estimation Using Backward Simulation
In this paper, we first derive a general multi-trajectory backward smoothing equation based on random finite sets of trajectories.
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular.
PMBM-based SLAM Filters in 5G mmWave Vehicular Networks
Secondly, the Poisson multi-Bernoulli (PMB) SLAM filter is based on the standard reduction from PMBM to PMB, but involves a novel interpretation based on auxiliary variables and a relation to Bethe free energy.
Active Learning with Weak Supervision for Gaussian Processes
Annotating data for supervised learning can be costly.
Object Detection as Probabilistic Set Prediction
Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems.
Can Deep Learning be Applied to Model-Based Multi-Object Tracking?
Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as autonomous driving, tracking animal behavior, defense systems, and others.
Iterated Posterior Linearization PMB Filter for 5G SLAM
In this paper, we study the linearization of the measurement function with respect to the posterior PDF, and implement the iterated posterior linearization filter into the Poisson multi-Bernoulli SLAM filter.
A time-weighted metric for sets of trajectories to assess multi-object tracking algorithms
This paper proposes a metric for sets of trajectories to evaluate multi-object tracking algorithms that includes time-weighted costs for localisation errors of properly detected targets, for false targets, missed targets and track switches.
A Computationally Efficient EK-PMBM Filter for Bistatic mmWave Radio SLAM
Millimeter wave (mmWave) signals are useful for simultaneous localization and mapping (SLAM), due to their inherent geometric connection to the propagation environment and the propagation channel.
Extended Object Tracking Using Sets Of Trajectories with a PHD Filter
PHD filtering is a common and effective multiple object tracking (MOT) algorithm used in scenarios where the number of objects and their states are unknown.
An Uncertainty-Aware Performance Measure for Multi-Object Tracking
Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context.
Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning
We show that the proposed model outperforms state-of-the-art Bayesian filters in complex scenarios, while matching their performance in simpler cases, which validates the applicability of deep-learning also in the model-based regime.
A Poisson multi-Bernoulli mixture filter for coexisting point and extended targets
This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter for coexisting point and extended targets, i. e., for scenarios where there may be simultaneous point and extended targets.
Backward Simulation for Sets of Trajectories
This paper presents a solution for recovering full trajectory information, via the calculation of the posterior of the set of trajectories, from a sequence of multitarget (unlabelled) filtering densities and the multitarget dynamic model.
DACS: Domain Adaptation via Cross-domain Mixed Sampling
In this paper we address the problem of unsupervised domain adaptation (UDA), which attempts to train on labelled data from one domain (source domain), and simultaneously learn from unlabelled data in the domain of interest (target domain).
Ranked #14 on
Domain Adaptation
on Cityscapes to ACDC
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation.
Exploiting Diffuse Multipath in 5G SLAM
5G millimeter wave (mmWave) signals can be used to jointly localize the receiver and map the propagation environment in vehicular networks, which is a typical simultaneous localization and mapping (SLAM) problem.
Trajectory Poisson multi-Bernoulli filters
The filters are based on propagating a Poisson multi-Bernoulli (PMB) density on the corresponding set of trajectories through the filtering recursion.
A general framework for ensemble distribution distillation
Ensembles of neural networks have been shown to give better performance than single networks, both in terms of predictions and uncertainty estimation.
Poisson Multi-Bernoulli Mixtures for Sets of Trajectories
First, we show that, for the standard point target model, the PMBM density is conjugate also for sets of trajectories.
Bayesian Linear Regression on Deep Representations
A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer.
Multi-Scan Implementation of the Trajectory Poisson Multi-Bernoulli Mixture Filter
A multi-scan trajectory PMBM filter and a multi-scan trajectory MBM filter, with the ability to correct past data association decisions to improve current decisions, are presented.
Signal Processing
Lidar-Camera Co-Training for Semi-Supervised Road Detection
Recent advances in the field of machine learning and computer vision have enabled the development of fast and accurate road detectors.
Extended target Poisson multi-Bernoulli mixture trackers based on sets of trajectories
The Poisson multi-Bernoulli mixture (PMBM) is a multi-target distribution for which the prediction and update are closed.
Signal Processing
Spooky effect in optimal OSPA estimation and how GOSPA solves it
In this paper, we show the spooky effect at a distance that arises in optimal estimation of multiple targets with the optimal sub-pattern assignment (OSPA) metric.
Gaussian implementation of the multi-Bernoulli mixture filter
This paper presents the Gaussian implementation of the multi-Bernoulli mixture (MBM) filter.
Poisson multi-Bernoulli mixture trackers: continuity through random finite sets of trajectories
By showing that the prediction and update in the PMBM filter can be viewed as an efficient method for calculating the time marginals of the RFS of trajectories, continuity in the same sense as MHT is established for the PMBM filter.
An Implementation of the Poisson Multi-Bernoulli Mixture Trajectory Filter via Dual Decomposition
This paper proposes an efficient implementation of the Poisson multi-Bernoulli mixture (PMBM) trajectory filter.
Trajectory PHD and CPHD filters
This paper presents the probability hypothesis density filter (PHD) and the cardinality PHD (CPHD) filter for sets of trajectories, which are referred to as the trajectory PHD (TPHD) and trajectory CPHD (TCPHD) filters.
Poisson Multi-Bernoulli Mapping Using Gibbs Sampling
The proposed method can handle uncertainties in the data associations and the cardinality of the set of landmarks, and is parallelizable, making it suitable for large-scale problems.
Infinite Factorial Finite State Machine for Blind Multiuser Channel Estimation
New communication standards need to deal with machine-to-machine communications, in which users may start or stop transmitting at any time in an asynchronous manner.
LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks
Whereas in the former two fusion approaches, the integration of multimodal information is carried out at a predefined depth level, the cross fusion FCN is designed to directly learn from data where to integrate information; this is accomplished by using trainable cross connections between the LIDAR and the camera processing branches.
Poisson Multi-Bernoulli Approximations for Multiple Extended Object Filtering
The Poisson multi-Bernoulli mixture (PMBM) is a multi-object conjugate prior for the closed-form Bayes random finite sets filter.
Imitation Learning for Vision-based Lane Keeping Assistance
This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera.
LIDAR-based Driving Path Generation Using Fully Convolutional Neural Networks
The fully convolutional neural network trained using all the available sensors together with driving directions achieved the best MaxF score of 88. 13% when considering a region of interest of 60x60 meters.
Poisson multi-Bernoulli mixture filter: direct derivation and implementation
We provide a derivation of the Poisson multi-Bernoulli mixture (PMBM) filter for multi-target tracking with the standard point target measurements without using probability generating functionals or functional derivatives.
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
The FCN is specifically designed for the task of pixel-wise semantic segmentation by combining a large receptive field with high-resolution feature maps.
Multiple target tracking based on sets of trajectories
We propose a solution of the multiple target tracking (MTT) problem based on sets of trajectories and the random finite set framework.
Trajectory probability hypothesis density filter
This paper presents the probability hypothesis density (PHD) filter for sets of trajectories: the trajectory probability density (TPHD) filter.
Poisson multi-Bernoulli conjugate prior for multiple extended object filtering
Both the prediction and the update preserve the PMBM form of the density, and in this sense the PMBM density is a conjugate prior.
A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithms
In this paper, we propose a metric on the space of finite sets of trajectories for assessing multi-target tracking algorithms in a mathematically sound way.
Generalized optimal sub-pattern assignment metric
This paper presents the generalized optimal sub-pattern assignment (GOSPA) metric on the space of finite sets of targets.
Infinite Factorial Dynamical Model
We propose the infinite factorial dynamic model (iFDM), a general Bayesian nonparametric model for source separation.
On the relation between Gaussian process quadratures and sigma-point methods
This article is concerned with Gaussian process quadratures, which are numerical integration methods based on Gaussian process regression methods, and sigma-point methods, which are used in advanced non-linear Kalman filtering and smoothing algorithms.
