no code implementations • 7 Mar 2024 • Martin Willbo, Aleksis Pirinen, John Martinsson, Edvin Listo Zec, Olof Mogren, Mikael Nilsson
In this work we systematically examine model sensitivities with respect to several color- and texture-based distortions on the input EO data during inference, given models that have been trained without such distortions.
1 code implementation • 23 Nov 2023 • Aleksis Pirinen, Nosheen Abid, Nuria Agues Paszkowsky, Thomas Ohlson Timoudas, Ronald Scheirer, Chiara Ceccobello, György Kovács, Anders Persson
To alleviate the COT data scarcity problem, in this work we propose a novel synthetic dataset for COT estimation, that we subsequently leverage for obtaining reliable and versatile cloud masks on real data.
1 code implementation • 4 Apr 2023 • Aleksis Pirinen, Olof Mogren, Mårten Västerdal
To the best of our knowledge, we are the first to tackle the task of dense water flow intensity prediction; earlier works have considered predicting flow intensities at a sparse set of locations at a time.
1 code implementation • 8 Sep 2022 • Aleksis Pirinen, Anton Samuelsson, John Backsund, Kalle Åström
To further mimic the situation on an actual UAV, the agent is not able to observe the search area in its entirety, not even at low resolution, and thus it has to operate solely based on partial glimpses when navigating towards the goal.
no code implementations • 28 Dec 2021 • David Nilsson, Aleksis Pirinen, Erik Gärtner, Cristian Sminchisescu
As we study this task in a lifelong learning context, the agents should use knowledge gained in earlier visited environments in order to guide their exploration and active learning strategy in successively visited buildings.
no code implementations • 17 Dec 2020 • David Nilsson, Aleksis Pirinen, Erik Gärtner, Cristian Sminchisescu
We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation.
1 code implementation • 7 Jan 2020 • Erik Gärtner, Aleksis Pirinen, Cristian Sminchisescu
Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given.
1 code implementation • NeurIPS 2019 • Aleksis Pirinen, Erik Gärtner, Cristian Sminchisescu
In order to address the view selection problem in a principled way, we here introduce ACTOR, an active triangulation agent for 3d human pose reconstruction.
1 code implementation • CVPR 2018 • Aleksis Pirinen, Cristian Sminchisescu
We propose drl-RPN, a deep reinforcement learning-based visual recognition model consisting of a sequential region proposal network (RPN) and an object detector.
no code implementations • CVPR 2016 • Stefan Mathe, Aleksis Pirinen, Cristian Sminchisescu
One of the most widely used strategies for visual object detection is based on exhaustive spatial hypothesis search.
no code implementations • 16 Mar 2016 • Aleksis Pirinen, Brendan Ames
As a model problem for clustering, we consider the densest k-disjoint-clique problem of partitioning a weighted complete graph into k disjoint subgraphs such that the sum of the densities of these subgraphs is maximized.