Search Results for author: Martin Jagersand

Found 35 papers, 16 papers with code

CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation

no code implementations17 Sep 2023 Chen Jiang, Yuchen Yang, Martin Jagersand

To generate high-quality segmentation predictions from referring expressions, we propose CLIPUNetr - a new CLIP-driven referring expression segmentation network.

Referring Expression Referring Expression Segmentation +2

Deep Probabilistic Movement Primitives with a Bayesian Aggregator

no code implementations11 Jul 2023 Michael Przystupa, Faezeh Haghverd, Martin Jagersand, Samuele Tosatto

Movement primitives are trainable parametric models that reproduce robotic movements starting from a limited set of demonstrations.

A Simple Decentralized Cross-Entropy Method

1 code implementation16 Dec 2022 Zichen Zhang, Jun Jin, Martin Jagersand, Jun Luo, Dale Schuurmans

To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a local improvement of its own sampling distribution.

Continuous Control Model-based Reinforcement Learning

Dynamic Decision Frequency with Continuous Options

1 code implementation6 Dec 2022 Amirmohammad Karimi, Jun Jin, Jun Luo, A. Rupam Mahmood, Martin Jagersand, Samuele Tosatto

In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals.

Continuous Control

Generalizable task representation learning from human demonstration videos: a geometric approach

no code implementations28 Feb 2022 Jun Jin, Martin Jagersand

We study the problem of generalizable task learning from human demonstration videos without extra training on the robot or pre-recorded robot motions.

Representation Learning

Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning

no code implementations29 Sep 2021 Zichen Zhang, Jun Jin, Martin Jagersand, Jun Luo, Dale Schuurmans

Further, we extend the decentralized approach to sequential decision-making problems where we show in 13 continuous control benchmark environments that it matches or outperforms the state-of-the-art CEM algorithms in most cases, under the same budget of the total number of samples for planning.

Continuous Control Decision Making +3

Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving

1 code implementation7 May 2021 Mennatullah Siam, Alex Kendall, Martin Jagersand

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects.

Autonomous Driving Contrastive Learning +2

Video Class Agnostic Segmentation Benchmark for Autonomous Driving

1 code implementation19 Mar 2021 Mennatullah Siam, Alex Kendall, Martin Jagersand

We formalize the task of video class agnostic segmentation from monocular video sequences in autonomous driving to account for unknown objects.

Autonomous Driving Instance Segmentation +3

Boundary-Aware Segmentation Network for Mobile and Web Applications

5 code implementations12 Jan 2021 Xuebin Qin, Deng-Ping Fan, Chenyang Huang, Cyril Diagne, Zichen Zhang, Adrià Cabeza Sant'Anna, Albert Suàrez, Martin Jagersand, Ling Shao

In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.

Camouflaged Object Segmentation Image Segmentation +3

Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning

no code implementations11 Nov 2020 Jun Jin, Daniel Graves, Cameron Haigh, Jun Luo, Martin Jagersand

We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills.

counterfactual reinforcement-learning +1

A Geometric Perspective on Visual Imitation Learning

no code implementations5 Mar 2020 Jun Jin, Laura Petrich, Masood Dehghan, Martin Jagersand

We consider the problem of visual imitation learning without human supervision (e. g. kinesthetic teaching or teleoperation), nor access to an interactive reinforcement learning (RL) training environment.

Imitation Learning Reinforcement Learning (RL)

Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream

1 code implementation2 Mar 2020 Chen Jiang, Masood Dehghan, Martin Jagersand

In this paper, to model the intended concepts of manipulation, we present a vision dataset under a strictly constrained knowledge domain for both robot and human manipulations, where manipulation concepts and relations are stored by an ontology system in a taxonomic manner.

Language Modelling

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

no code implementations26 Jan 2020 Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand

Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels.

Few-Shot Learning Object +5

One-Shot Weakly Supervised Video Object Segmentation

no code implementations18 Dec 2019 Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand

Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks.

Object Segmentation +4

Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans

no code implementations8 Nov 2019 Jun Jin, Nhat M. Nguyen, Nazmus Sakib, Daniel Graves, Hengshuai Yao, Martin Jagersand

We observe that our method demonstrates time-efficient path planning behavior with high success rate in mapless navigation tasks.


Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks

no code implementations16 Sep 2019 Chen Jiang, Martin Jagersand

Using the framework, we present a case study where robot performs manipulation actions in a kitchen environment, bridging visual perception with contextual semantics using the generated dynamic knowledge graphs.

Attribute Common Sense Reasoning +3

Adaptive Masked Proxies for Few-Shot Segmentation

1 code implementation19 Feb 2019 Mennatullah Siam, Boris Oreshkin, Martin Jagersand

Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation.

Continual Learning Few-Shot Semantic Segmentation +4

Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting

1 code implementation17 Oct 2018 Mennatullah Siam, Chen Jiang, Steven Lu, Laura Petrich, Mahmoud Gamal, Mohamed Elhoseiny, Martin Jagersand

A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels.

Incremental Learning Robot Manipulation +4

Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach

1 code implementation29 Sep 2018 Jun Jin, Laura Petrich, Masood Dehghan, Zichen Zhang, Martin Jagersand

Our proposed method can directly learn from raw videos, which removes the need for hand-engineered task specification.


RTSeg: Real-time Semantic Segmentation Comparative Study

2 code implementations7 Mar 2018 Mennatullah Siam, Mostafa Gamal, Moemen Abdel-Razek, Senthil Yogamani, Martin Jagersand

In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods.

Autonomous Driving Benchmarking +2

End-to-end detection-segmentation network with ROI convolution

1 code implementation8 Jan 2018 Zichen Zhang, Min Tang, Dana Cobzas, Dornoosh Zonoobi, Martin Jagersand, Jacob L. Jaremko

We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit.

Object Localization Segmentation

Incremental 3D Line Segment Extraction from Semi-dense SLAM

1 code implementation10 Aug 2017 Shida He, Xuebin Qin, Zichen Zhang, Martin Jagersand

This approach reduces a 3D line segment fitting problem into two 2D line segment fitting problems and takes advantage of both images and depth maps.

Clustering Simultaneous Localization and Mapping +1

Real-Time Salient Closed Boundary Tracking via Line Segments Perceptual Grouping

2 code implementations30 Apr 2017 Xuebin Qin, Shida He, Camilo Perez Quintero, Abhineet Singh, Masood Dehghan, Martin Jagersand

The tracking scheme is coherently integrated into a perceptual grouping framework in which the visual tracking problem is tackled by identifying a subset of these line segments and connecting them sequentially to form a closed boundary with the largest saliency and a certain similarity to the previous one.

Line Detection Visual Tracking

4-DoF Tracking for Robot Fine Manipulation Tasks

no code implementations6 Mar 2017 Mennatullah Siam, Abhineet Singh, Camilo Perez, Martin Jagersand

One of these trackers is a newly developed learning based tracker that relies on learning discriminative correlation filters while the other is a refinement of a recent 8 DoF RANSAC based tracker adapted with a new appearance model for tracking 4 DoF motion.

Incremental Learning for Robot Perception through HRI

no code implementations17 Jan 2017 Sepehr Valipour, Camilo Perez, Martin Jagersand

Given this information, the robot visually explores the object and adds images from it to re-train the perception module.

Incremental Learning Object +4

Unifying Registration based Tracking: A Case Study with Structural Similarity

1 code implementation15 Jul 2016 Abhineet Singh, Mennatullah Siam, Martin Jagersand

This paper adapts a popular image quality measure called structural similarity for high precision registration based tracking while also introducing a simpler and faster variant of the same.

Parking Stall Vacancy Indicator System Based on Deep Convolutional Neural Networks

no code implementations30 Jun 2016 Sepehr Valipour, Mennatullah Siam, Eleni Stroulia, Martin Jagersand

Visual detection methods represent a cost-effective option, since they can take advantage of hardware usually already available in many parking lots, namely cameras.


Recurrent Fully Convolutional Networks for Video Segmentation

no code implementations1 Jun 2016 Sepehr Valipour, Mennatullah Siam, Martin Jagersand, Nilanjan Ray

Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data.

Change Detection Image Segmentation +4

Modular Decomposition and Analysis of Registration based Trackers

no code implementations3 Mar 2016 Abhineet Singh, Ankush Roy, Xi Zhang, Martin Jagersand

We show how existing trackers can be broken down using the suggested methodology and compare the performance of the default configuration chosen by the authors against other possible combinations to demonstrate the new insights that can be gained by such an approach.

Modular Tracking Framework: A Unified Approach to Registration based Tracking

1 code implementation29 Feb 2016 Abhineet Singh, Martin Jagersand

This paper presents a modular, extensible and highly efficient open source framework for registration based tracking called Modular Tracking Framework (MTF).

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