4 papers
Uncertainty Estimation in Instance Segmentation of Affordances via Bayesian Visual Transformers
Lorenzo Mur-Labadia, Ruben Martinez-Cantina, Jose J. Guerrero
Visual affordances identify regions in an image with potential interactions, offering a novel paradigm for scene understanding. Recognizing affordances allows autonomous robots to…
SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation
Cesar Borja, Carlos Plou, Ruben Martinez-Cantin +1
Semantic segmentation is essential for automating remote sensing analysis in fields like ecology. However, fine-grained analysis of complex aerial or underwater imagery remains an…
On the Uncertain Single-View Depths in Colonoscopies
Javier Rodríguez-Puigvert, David Recasens, Javier Civera +1
Estimating depth information from endoscopic images is a prerequisite for a wide set of AI-assisted technologies, such as accurate localization and measurement of tumors, or identi…
Bayesian Deep Neural Networks for Supervised Learning of Single-View Depth
Javier Rodríguez-Puigvert, Rubén Martínez-Cantín, Javier Civera
Uncertainty quantification is essential for robotic perception, as overconfident or point estimators can lead to collisions and damages to the environment and the robot. In this pa…