Search Results for author: Álvaro García-Martín

Found 8 papers, 6 papers with code

SynthmanticLiDAR: A Synthetic Dataset for Semantic Segmentation on LiDAR Imaging

1 code implementation31 Jan 2025 Javier Montalvo, Pablo Carballeira, Álvaro García-Martín

In this work, we present a modified CARLA simulator designed with LiDAR semantic segmentation in mind, with new classes, more consistent object labeling with their counterparts from real datasets such as SemanticKITTI, and the possibility to adjust the object class distribution.

Autonomous Driving LIDAR Semantic Segmentation +3

Unsupervised Class Generation to Expand Semantic Segmentation Datasets

no code implementations4 Jan 2025 Javier Montalvo, Álvaro García-Martín, Pablo Carballeira, Juan C. SanMiguel

To mitigate this cost there has been a surge in the use of synthetically generated data -- usually created using simulators or videogames -- which, in combination with domain adaptation methods, can effectively learn how to segment real data.

Segmentation Semantic Segmentation +1

Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances

no code implementations21 Dec 2024 Javier Montalvo, Roberto Alcover-Couso, Pablo Carballeira, Álvaro García-Martín, Juan C. SanMiguel, Marcos Escudero-Viñolo

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains.

Contrastive Learning Domain Adaptation +3

Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis

1 code implementation5 Oct 2024 Juan Ignacio Bravo Pérez-Villar, Álvaro García-Martín, Jesús Bescós, Juan C. SanMiguel

Due to the difficulty of replicating the real conditions during training, supervised algorithms for spacecraft pose estimation experience a drop in performance when trained on synthetic data and applied to real operational data.

Image Generation Pose Estimation +3

Improved transferability of self-supervised learning models through batch normalization finetuning

1 code implementation Applied Intelligence 2024 Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira, Álvaro García-Martín

At a cost of extra training of only 0. 16% model parameters, in case of ResNet-50, we acquire a proxy task that (i) has a stronger correlation with end-to-end finetuned performance, (ii) improves the linear probing performance in the many- and few-shot learning regimes and (iii) in some cases, outperforms both linear probing and end-to-end finetuning, reaching the state-of-the-art performance on a pathology dataset.

 Ranked #1 on Classification on MHIST (using extra training data)

Classification Few-Shot Learning +2

SPIN: Spacecraft Imagery for Navigation

1 code implementation11 Jun 2024 Javier Montalvo, Juan Ignacio Bravo Pérez-Villar, Álvaro García-Martín, Pablo Carballeira, Jesús Bescós

To address these limitations, we present SPIN (SPacecraft Imagery for Navigation), an open-source spacecraft image generation tool designed to support a wide range of visual navigation scenarios in space, with a particular focus on relative navigation tasks.

Data Augmentation Image Generation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.