5 citations · 18 across the 15 of their papers we have counts for
15 papers
Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder
Alaa Yasser, Kittipat Phunjanna, Marcos Escudero Viñolo +2
Standard fairness audits of foundation models quantify that a model is biased, but not where inside the network the bias resides. We propose a mechanistic fairness audit that combi…
Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances
Javier Montalvo, Roberto Alcover-Couso, Pablo Carballeira +3
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…
VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation
Roberto Alcover-Couso, Marcos Escudero-Viñolo, Juan C. SanMiguel +1
Segmentation models are typically constrained by the categories defined during training. To address this, researchers have explored two independent approaches: adapting Vision-Lang…
Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira +3
Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce a…
Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
Roberto Alcover-Couso, Juan C. SanMiguel, Marcos Escudero-Viñolo +1
Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble cr…
Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks
Roberto Alcover-Couso, Marcos Escudero-Viñolo, Juan C. SanMiguel +1
In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, address…
The Robust Semantic Segmentation UNCV2023 Challenge Results
Xuanlong Yu, Yi Zuo, Zitao Wang +34
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segment…
Soft labelling for semantic segmentation: Bringing coherence to label down-sampling
Roberto Alcover-Couso, Marcos Escudero-Vinolo, Juan C. SanMiguel +1
In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation.…
Self-Supervised Curricular Deep Learning for Chest X-Ray Image Classification
Iván de Andrés Tamé, Kirill Sirotkin, Pablo Carballeira +1
Deep learning technologies have already demonstrated a high potential to build diagnosis support systems from medical imaging data, such as Chest X-Ray images. However, the shortag…
Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking
Elena Luna, Juan Carlos San Miguel, José María Martínez +1
This letter focuses on the task of Multi-Target Multi-Camera vehicle tracking. We propose to associate single-camera trajectories into multi-camera global trajectories by training…
Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss
Alejandro López-Cifuentes, Marcos Escudero-Viñolo, Jesús Bescós +1
Knowledge Distillation (KD) is a strategy for the definition of a set of transferability gangways to improve the efficiency of Convolutional Neural Networks. Feature-based Knowledg…
A study on the distribution of social biases in self-supervised learning visual models
Kirill Sirotkin, Pablo Carballeira, Marcos Escudero-Viñolo
Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorpor…
Improved skin lesion recognition by a Self-Supervised Curricular Deep Learning approach
Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira +1
State-of-the-art deep learning approaches for skin lesion recognition often require pretraining on larger and more varied datasets, to overcome the generalization limitations deriv…
Online Clustering-based Multi-Camera Vehicle Tracking in Scenarios with overlapping FOVs
Elena Luna, Juan C. SanMiguel, Jose M. Martínez +1
Multi-Target Multi-Camera (MTMC) vehicle tracking is an essential task of visual traffic monitoring, one of the main research fields of Intelligent Transportation Systems. Several…
Egocentric Human Segmentation for Mixed Reality
Andrija Gajic, Ester Gonzalez-Sosa, Diego Gonzalez-Morin +2
The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks. Our contribution is two-fold: i) we create a semi-synthetic da…