KTH Royal Institute of Technology

research

∙ 11/27/2019

Shearlets as Feature Extractor for Semantic Edge Detection: The Model-Based and Data-Driven Realm

Semantic edge detection has recently gained a lot of attention as an ima...

Héctor Andrade-Loarca, et al. ∙

research

∙ 01/24/2020

Kernel of CycleGAN as a Principle homogeneous space

Unpaired image-to-image translation has attracted significant interest d...

Nikita Moriakov, et al. ∙

research

∙ 11/14/2018

Deep Bayesian Inversion

Characterizing statistical properties of solutions of inverse problems i...

Jonas Adler, et al. ∙

research

∙ 07/02/2020

Human-centered collaborative robots with deep reinforcement learning

We present a reinforcement learning based framework for human-centered c...

Ali Ghadirzadeh, et al. ∙

research

∙ 07/11/2020

Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models

The ability to accurately estimate risk of developing breast cancer woul...

Yue Liu, et al. ∙

research

∙ 09/30/2020

The Importance of Balanced Data Sets: Analyzing a Vehicle Trajectory Prediction Model based on Neural Networks and Distributed Representations

Predicting future behavior of other traffic participants is an essential...

Florian Mirus, et al. ∙

research

∙ 08/20/2021

Is it Time to Replace CNNs with Transformers for Medical Images?

Convolutional Neural Networks (CNNs) have reigned for a decade as the de...

Christos Matsoukas, et al. ∙

research

∙ 01/30/2020

Which way? Direction-Aware Attributed Graph Embedding

Graph embedding algorithms are used to efficiently represent (encode) a ...

Zekarias T. Kefato, et al. ∙

research

∙ 10/14/2019

Imitating by generating: deep generative models for imitation of interactive tasks

To coordinate actions with an interaction partner requires a constant ex...

Judith Butepage, et al. ∙

research

∙ 12/23/2019

Neural Outlier Rejection for Self-Supervised Keypoint Learning

Identifying salient points in images is a crucial component for visual o...

Jiexiong Tang, et al. ∙

research

∙ 03/17/2020

Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator

We provide a new finite-time analysis of the estimation error of stable ...

Yassir Jedra, et al. ∙

research

∙ 05/13/2020

Coordinates-based Resource Allocation Through Supervised Machine Learning

Appropriate allocation of system resources is essential for meeting the ...

Sahar Imtiaz, et al. ∙

research

∙ 02/28/2019

GCNv2: Efficient Correspondence Prediction for Real-Time SLAM

In this paper, we present a deep learning-based network, GCNv2, for gene...

Jiexiong Tang, et al. ∙

research

∙ 01/22/2020

Machine Learning assisted Handover and Resource Management for Cellular Connected Drones

Enabling cellular connectivity for drones introduces a wide set of chall...

Amin Azari, et al. ∙

research

∙ 09/30/2020

Analyzing the Capacity of Distributed Vector Representations to Encode Spatial Information

Vector Symbolic Architectures belong to a family of related cognitive mo...

Florian Mirus, et al. ∙

research

∙ 03/17/2020

Hyperplane Arrangements of Trained ConvNets Are Biased

We investigate the geometric properties of the functions learned by trai...

Matteo Gamba, et al. ∙

research

∙ 09/15/2021

Balancing detectability and performance of attacks on the control channel of Markov Decision Processes

We investigate the problem of designing optimal stealthy poisoning attac...

Alessio Russo, et al. ∙

research

∙ 06/27/2020

α Belief Propagation for Approximate Inference

Belief propagation (BP) algorithm is a widely used message-passing metho...

Dong Liu, et al. ∙

research

∙ 02/26/2019

Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions

We propose a developmental approach that allows a robot to interpret and...

Giovanni Saponaro, et al. ∙

research

∙ 03/21/2019

Sparse2Dense: From direct sparse odometry to dense 3D reconstruction

In this paper, we proposed a new deep learning based dense monocular SLA...

Jiexiong Tang, et al. ∙

research

∙ 08/01/2019

A Framework for Depth Estimation and Relative Localization of Ground Robots using Computer Vision

The 3D depth estimation and relative pose estimation problem within a de...

Romulo T. Rodrigues, et al. ∙

research

∙ 08/30/2021

Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation

Timely detection of horse pain is important for equine welfare. Horses e...

Maheen Rashid, et al. ∙

research

∙ 09/17/2021

Enforcing fairness in private federated learning via the modified method of differential multipliers

Federated learning with differential privacy, or private federated learn...

Borja Rodríguez Gálvez, et al. ∙

research

∙ 01/18/2022

AI-Aided Integrated Terrestrial and Non-Terrestrial 6G Solutions for Sustainable Maritime Networking

The maritime industry is experiencing a technological revolution that af...

Salwa Saafi, et al. ∙

research

∙ 07/31/2019

Neural Network based Explicit Mixture Models and Expectation-maximization based Learning

We propose two neural network based mixture models in this article. The ...

Dong Liu, et al. ∙

research

∙ 01/22/2021

Tighter expected generalization error bounds via Wasserstein distance

In this work, we introduce several expected generalization error bounds ...

Borja Rodríguez Gálvez, et al. ∙

research

∙ 11/16/2018

Entropy-regularized Optimal Transport Generative Models

We investigate the use of entropy-regularized optimal transport (EOT) co...

Dong Liu, et al. ∙

research

∙ 01/03/2019

A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels

Image classification models built into visual support systems and other ...

Marcus Klasson, et al. ∙

research

∙ 06/16/2020

Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks

Visual relationship detection is fundamental for holistic image understa...

Federico Baldassarre, et al. ∙

research

∙ 06/26/2020

Incremental inference of collective graphical models

We consider incremental inference problems from aggregate data for colle...

Rahul Singh, et al. ∙

research

∙ 06/18/2021

hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition

In this paper we present our preliminary work on model-based behavioral ...

Ci Li, et al. ∙

research

∙ 12/02/2021

CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer

Interval and large invasive breast cancers, which are associated with wo...

Moein Sorkhei, et al. ∙

research

∙ 01/21/2022

Accelerate Model Parallel Training by Using Efficient Graph Traversal Order in Device Placement

Modern neural networks require long training to reach decent performance...

Tianze Wang, et al. ∙

research

∙ 08/23/2019

α Belief Propagation as Fully Factorized Approximation

Belief propagation (BP) can do exact inference in loop-free graphs, but ...

Dong Liu, et al. ∙

research

∙ 01/27/2020

Bayesian nonparametric shared multi-sequence time series segmentation

In this paper, we introduce a method for segmenting time series data usi...

Olga Mikheeva, et al. ∙

research

∙ 06/18/2018

Banach Wasserstein GAN

Wasserstein Generative Adversarial Networks (WGANs) can be used to gener...

Jonas Adler, et al. ∙

research

∙ 07/31/2019

Optimal Attacks on Reinforcement Learning Policies

Control policies, trained using the Deep Reinforcement Learning, have be...

Alessio Russo, et al. ∙

research

∙ 06/25/2021

Transflower: probabilistic autoregressive dance generation with multimodal attention

Dance requires skillful composition of complex movements that follow rhy...

Guillermo Valle Pérez, et al. ∙

research

∙ 05/12/2020

A Survey of Behavior Trees in Robotics and AI

Behavior Trees (BTs) were invented as a tool to enable modular AI in com...

Matteo Iovino, et al. ∙

research

∙ 06/17/2021

Is Channel Estimation Necessary to Select Phase-Shifts for RIS-Assisted Massive MIMO?

Reconfigurable intelligent surfaces (RISs) have attracted great attentio...

Özlem Tugfe Demir, et al. ∙

research

∙ 09/07/2016

Distributed sampled-data control of nonholonomic multi-robot systems with proximity networks

This paper considers the distributed sampled-data control problem of a g...

Zhixin Liu, et al. ∙

research

∙ 11/24/2017

Interactive Robot Learning of Gestures, Language and Affordances

A growing field in robotics and Artificial Intelligence (AI) research is...

Giovanni Saponaro, et al. ∙

research

∙ 11/24/2017

Self-Supervised Vision-Based Detection of the Active Speaker as a Prerequisite for Socially-Aware Language Acquisition

This paper presents a self-supervised method for detecting the active sp...

Kalin Stefanov, et al. ∙

research

∙ 11/01/2017

Minimal Exploration in Structured Stochastic Bandits

This paper introduces and addresses a wide class of stochastic bandit pr...

Richard Combes, et al. ∙

research

∙ 11/15/2017

Advances in Variational Inference

Many modern unsupervised or semi-supervised machine learning algorithms ...

Cheng Zhang, et al. ∙

research

∙ 07/20/2017

Learned Primal-dual Reconstruction

We propose the Learned Primal-Dual algorithm for tomographic reconstruct...

Jonas Adler, et al. ∙

research

∙ 09/05/2017

Machine Learning and Social Robotics for Detecting Early Signs of Dementia

This paper presents the EACare project, an ambitious multi-disciplinary ...

Patrik Jonell, et al. ∙

research

∙ 01/18/2017

On the Performance of Network Parallel Training in Artificial Neural Networks

Artificial Neural Networks (ANNs) have received increasing attention in ...

Ludvig Ericson, et al. ∙

research

∙ 10/30/2017

Learning to solve inverse problems using Wasserstein loss

We propose using the Wasserstein loss for training in inverse problems. ...

Jonas Adler, et al. ∙

research

∙ 10/18/2017

Unsupervised Object Discovery and Segmentation of RGBD-images

In this paper we introduce a system for unsupervised object discovery an...

Johan Ekekrantz, et al. ∙

KTH Royal Institute of Technology

Featured Researchers