Search Results for author: Mårten Björkman

Found 19 papers, 3 papers with code

On the Lipschitz Constant of Deep Networks and Double Descent

no code implementations28 Jan 2023 Matteo Gamba, Hossein Azizpour, Mårten Björkman

Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms controlling such factors in practice.

Deep Double Descent via Smooth Interpolation

no code implementations21 Sep 2022 Matteo Gamba, Erik Englesson, Mårten Björkman, Hossein Azizpour

The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error.

Dance Style Transfer with Cross-modal Transformer

no code implementations19 Aug 2022 Wenjie Yin, Hang Yin, Kim Baraka, Danica Kragic, Mårten Björkman

We present CycleDance, a dance style transfer system to transform an existing motion clip in one dance style to a motion clip in another dance style while attempting to preserve motion context of the dance.

Style Transfer

On the Subspace Structure of Gradient-Based Meta-Learning

no code implementations8 Jul 2022 Gustaf Tegnér, Alfredo Reichlin, Hang Yin, Mårten Björkman, Danica Kragic

In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods.

Few-Shot Learning Image Classification +1

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

no code implementations18 Apr 2022 Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making reinforcement-learning +2

Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Series

no code implementations20 May 2021 Shuangshuang Chen, Sihao Ding, Yiannis Karayiannidis, Mårten Björkman

Learning generative models and inferring latent trajectories have shown to be challenging for time series due to the intractable marginal likelihoods of flexible generative models.

Time Series Analysis

Graph-based Normalizing Flow for Human Motion Generation and Reconstruction

no code implementations7 Apr 2021 Wenjie Yin, Hang Yin, Danica Kragic, Mårten Björkman

Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics.

Combining Planning and Learning of Behavior Trees for Robotic Assembly

1 code implementation16 Mar 2021 Jonathan Styrud, Matteo Iovino, Mikael Norrlöf, Mårten Björkman, Christian Smith

Industrial robots can solve very complex tasks in controlled environments, but modern applications require robots able to operate in unpredictable surroundings as well.

Industrial Robots


no code implementations ICLR Workshop Learning_to_Learn 2021 Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic

Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.

Meta-Learning Variational Inference

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

no code implementations5 Mar 2021 Ali Ghadirzadeh, Xi Chen, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic

Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.


Data-efficient visuomotor policy training using reinforcement learning and generative models

no code implementations26 Jul 2020 Ali Ghadirzadeh, Petra Poklukar, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making Disentanglement +3

Hyperplane Arrangements of Trained ConvNets Are Biased

1 code implementation17 Mar 2020 Matteo Gamba, Stefan Carlsson, Hossein Azizpour, Mårten Björkman

We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of hyperplane arrangements induced by a convolutional layer.

Adversarial Feature Training for Generalizable Robotic Visuomotor Control

no code implementations17 Sep 2019 Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs.

Transfer Learning

Meta-Learning for Multi-objective Reinforcement Learning

no code implementations8 Nov 2018 Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives.

Continuous Control Decision Making +3

Feature Descriptors for Tracking by Detection: a Benchmark

no code implementations21 Jul 2016 Alessandro Pieropan, Mårten Björkman, Niklas Bergström, Danica Kragic

In this paper, we provide an extensive evaluation of the performance of local descriptors for tracking applications.

3D Reconstruction Object Recognition

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