3 papers
cs.CV2021
Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches
Jose L. Gómez, Gabriel Villalonga, Antonio M. López
Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated…
cs.CV2020
Co-training for On-board Deep Object Detection
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. This w…
cs.CV2019
Temporal Coherence for Active Learning in Videos
Javad Zolfaghari Bengar, Abel Gonzalez-Garcia, Gabriel Villalonga +5
Autonomous driving systems require huge amounts of data to train. Manual annotation of this data is time-consuming and prohibitively expensive since it involves human resources. Th…