5 citations · 8 across the 4 of their papers we have counts for
4 papers
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…
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…
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…