Alert button
Picture for Adriana Romero-Soriano

Adriana Romero-Soriano

Alert button

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning

Jan 09, 2024
Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano, Reihaneh Rabbany

Viaarxiv icon

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions

Dec 14, 2023
Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson, Vasu Sharma, Adriana Romero-Soriano

Viaarxiv icon

Feedback-guided Data Synthesis for Imbalanced Classification

Sep 29, 2023
Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano

Viaarxiv icon

Graph Inductive Biases in Transformers without Message Passing

May 27, 2023
Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim

Figure 1 for Graph Inductive Biases in Transformers without Message Passing
Figure 2 for Graph Inductive Biases in Transformers without Message Passing
Figure 3 for Graph Inductive Biases in Transformers without Message Passing
Figure 4 for Graph Inductive Biases in Transformers without Message Passing
Viaarxiv icon

Improved baselines for vision-language pre-training

May 15, 2023
Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal

Figure 1 for Improved baselines for vision-language pre-training
Figure 2 for Improved baselines for vision-language pre-training
Figure 3 for Improved baselines for vision-language pre-training
Figure 4 for Improved baselines for vision-language pre-training
Viaarxiv icon

Controllable Image Generation via Collage Representations

Apr 26, 2023
Arantxa Casanova, Marlène Careil, Adriana Romero-Soriano, Christopher J. Pal, Jakob Verbeek, Michal Drozdzal

Figure 1 for Controllable Image Generation via Collage Representations
Figure 2 for Controllable Image Generation via Collage Representations
Figure 3 for Controllable Image Generation via Collage Representations
Figure 4 for Controllable Image Generation via Collage Representations
Viaarxiv icon

Instance-Conditioned GAN Data Augmentation for Representation Learning

Mar 16, 2023
Pietro Astolfi, Arantxa Casanova, Jakob Verbeek, Pascal Vincent, Adriana Romero-Soriano, Michal Drozdzal

Figure 1 for Instance-Conditioned GAN Data Augmentation for Representation Learning
Figure 2 for Instance-Conditioned GAN Data Augmentation for Representation Learning
Figure 3 for Instance-Conditioned GAN Data Augmentation for Representation Learning
Figure 4 for Instance-Conditioned GAN Data Augmentation for Representation Learning
Viaarxiv icon

Learning to Substitute Ingredients in Recipes

Feb 15, 2023
Bahare Fatemi, Quentin Duval, Rohit Girdhar, Michal Drozdzal, Adriana Romero-Soriano

Figure 1 for Learning to Substitute Ingredients in Recipes
Figure 2 for Learning to Substitute Ingredients in Recipes
Figure 3 for Learning to Substitute Ingredients in Recipes
Figure 4 for Learning to Substitute Ingredients in Recipes
Viaarxiv icon

On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects

Jan 02, 2023
Sumana Basu, Marc-André Legault, Adriana Romero-Soriano, Doina Precup

Figure 1 for On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects
Figure 2 for On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects
Figure 3 for On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects
Figure 4 for On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects
Viaarxiv icon