Search Results for author:
Found 11 papers, 6 papers with code
Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning
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.
Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI
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.
Fully Convolutional Networks for Dense Water Flow Intensity Prediction in Swedish Catchment Areas
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.
Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescue
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.
Embodied Learning for Lifelong Visual Perception
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.
Embodied Visual Active Learning for Semantic Segmentation
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.
Deep Reinforcement Learning for Active Human Pose Estimation
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.
Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction
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.
Deep Reinforcement Learning of Region Proposal Networks for Object Detection
We propose drl-RPN, a deep reinforcement learning-based visual recognition model consisting of a sequential region proposal network (RPN) and an object detector.
Reinforcement Learning for Visual Object Detection
One of the most widely used strategies for visual object detection is based on exhaustive spatial hypothesis search.
Exact Clustering of Weighted Graphs via Semidefinite Programming
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.
