no code implementations • 17 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.
no code implementations • 11 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.
1 code implementation • 16 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.
1 code implementation • 6 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.
no code implementations • 28 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.
no code implementations • 29 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.
1 code implementation • 7 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.
1 code implementation • 19 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.
5 code implementations • 12 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.
no code implementations • 11 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.
28 code implementations • 18 May 2020 • Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane, Martin Jagersand
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).
Ranked #1 on Salient Object Detection on SOD
no code implementations • 5 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.
1 code implementation • 2 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.
no code implementations • 26 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.
no code implementations • 18 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.
no code implementations • 8 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.
Robotics
no code implementations • 16 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.
1 code implementation • 19 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.
1 code implementation • 17 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.
1 code implementation • 29 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.
Robotics
2 code implementations • 7 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.
1 code implementation • 8 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.
no code implementations • 31 Oct 2017 • Min Tang, Zichen Zhang, Dana Cobzas, Martin Jagersand, Jacob L. Jaremko
We propose an attention mechanism for 3D medical image segmentation.
no code implementations • 14 Sep 2017 • Mennatullah Siam, Heba Mahgoub, Mohamed Zahran, Senthil Yogamani, Martin Jagersand, Ahmad El-Sallab
Our experiments show that the proposed method outperforms state of the art methods that utilize motion cue only with 21. 5% in mAP on KITTI MOD.
1 code implementation • 10 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.
no code implementations • 8 Jul 2017 • Mennatullah Siam, Sara Elkerdawy, Martin Jagersand, Senthil Yogamani
In this paper, the semantic segmentation problem is explored from the perspective of automated driving.
2 code implementations • 30 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.
no code implementations • 6 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.
no code implementations • 17 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.
no code implementations • 16 Nov 2016 • Mennatullah Siam, Sepehr Valipour, Martin Jagersand, Nilanjan Ray
This architecture is tested for both binary and semantic video segmentation tasks.
1 code implementation • 15 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.
no code implementations • 30 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.
no code implementations • 1 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.
no code implementations • 3 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.
1 code implementation • 29 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).