no code implementations • 30 Aug 2019 • Javad Zolfaghari Bengar, Abel Gonzalez-Garcia, Gabriel Villalonga, Bogdan Raducanu, Hamed H. Aghdam, Mikhail Mozerov, Antonio M. Lopez, Joost Van de Weijer
Our active learning criterion is based on the estimated number of errors in terms of false positives and false negatives.
no code implementations • 12 Aug 2020 • Gabriel Villalonga, Antonio M. Lopez
Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models.
no code implementations • 23 Apr 2021 • Jose L. Gómez, Gabriel Villalonga, Antonio M. López
This data labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling.
1 code implementation • 31 May 2022 • Jose L. Gómez, Gabriel Villalonga, Antonio M. López
In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models.
no code implementations • 30 Apr 2024 • Diego Porres, Yi Xiao, Gabriel Villalonga, Alexandre Levy, Antonio M. López
Vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving.