Portrait of Adriana Romero Soriano

Adriana Romero Soriano

Core Industry Member
Canada CIFAR AI Chair
Adjunct professor, McGill University, School of Computer Science
Research Scientist, Meta AI Research (FAIR)
Research Topics
Computer Vision
Deep Learning
Generative Models

Biography

Adriana Romero-Soriano is a research scientist in the Fundamental AI Research (FAIR) team at Meta, adjunct professor at McGill University, core industry member of Mila – Quebec Artificial Intelligence Institute and a Canada CIFAR AI Chair.

Romero-Soriano’s research lies at the intersection of generative models, computer vision and responsible AI, while her most recent work focuses on improving the quality, controllability, consistency and representation diversity of visual content creation systems.

She received her PhD from the University of Barcelona, where she worked with Carlo Gatta, and then spent two years as a postdoctoral researcher at Mila with Yoshua Bengio.

Current Students

Collaborating researcher - Université de Montréal
PhD - McGill University
Principal supervisor :
PhD - McGill University
Principal supervisor :

Publications

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs
Aarash Feizi
Sai Rajeswar
Spandana Gella
Valentina Zantedeschi
Joao Monteiro
As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare dat… (see more)a pairs as instructed in the prompt becomes essential. To address this, we present PairBench, a low-cost framework that systematically evaluates VLMs as customizable similarity tools across various modalities and scenarios. Through PairBench, we introduce four metrics that represent key desiderata of similarity scores: alignment with human annotations, consistency for data pairs irrespective of their order, smoothness of similarity distributions, and controllability through prompting. Our analysis demonstrates that no model, whether closed- or open-source, is superior on all metrics; the optimal choice depends on an auto evaluator's desired behavior (e.g., a smooth vs. a sharp judge), highlighting risks of widespread adoption of VLMs as evaluators without thorough assessment. For instance, the majority of VLMs struggle with maintaining symmetric similarity scores regardless of order. Additionally, our results show that the performance of VLMs on the metrics in PairBench closely correlates with popular benchmarks, showcasing its predictive power in ranking models.
What makes a good metric? Evaluating automatic metrics for text-to-image consistency
Candace Ross
Melissa Hall
Adina Williams
Language models are increasingly being incorporated as components in larger AI systems for various purposes, from prompt optimization to aut… (see more)omatic evaluation. In this work, we analyze the construct validity of four recent, commonly used methods for measuring text-to-image consistency - CLIPScore, TIFA, VPEval, and DSG - which rely on language models and/or VQA models as components. We define construct validity for text-image consistency metrics as a set of desiderata that text-image consistency metrics should have, and find that no tested metric satisfies all of them. We find that metrics lack sufficient sensitivity to language and visual properties. Next, we find that TIFA, VPEval and DSG contribute novel information above and beyond CLIPScore, but also that they correlate highly with each other. We also ablate different aspects of the text-image consistency metrics and find that not all model components are strictly necessary, also a symptom of insufficient sensitivity to visual information. Finally, we show that all three VQA-based metrics likely rely on familiar text shortcuts (such as yes-bias in QA) that call their aptitude as quantitative evaluations of model performance into question.
What makes a good metric? Evaluating automatic metrics for text-to-image consistency
Candace Ross
Melissa Hall
Adina Williams
Language models are increasingly being incorporated as components in larger AI systems for various purposes, from prompt optimization to aut… (see more)omatic evaluation. In this work, we analyze the construct validity of four recent, commonly used methods for measuring text-to-image consistency - CLIPScore, TIFA, VPEval, and DSG - which rely on language models and/or VQA models as components. We define construct validity for text-image consistency metrics as a set of desiderata that text-image consistency metrics should have, and find that no tested metric satisfies all of them. We find that metrics lack sufficient sensitivity to language and visual properties. Next, we find that TIFA, VPEval and DSG contribute novel information above and beyond CLIPScore, but also that they correlate highly with each other. We also ablate different aspects of the text-image consistency metrics and find that not all model components are strictly necessary, also a symptom of insufficient sensitivity to visual information. Finally, we show that all three VQA-based metrics likely rely on familiar text shortcuts (such as yes-bias in QA) that call their aptitude as quantitative evaluations of model performance into question.
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall
Oscar Mañas
Reyhane Askari
Mark Ibrahim
Candace Ross
Pietro Astolfi
Tariq Berrada
Marton Havasi
Yohann Benchetrit
Karen Ullrich
Carolina Braga
Abhishek Charnalia
Maeve Ryan
Michael Rabbat
Michal Drozdzal
Jakob Verbeek
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. Ho… (see more)wever, while metrics and datasets abound, there are few unified benchmarking libraries that provide a framework for performing evaluations across many datasets and metrics. Furthermore, the rapid introduction of increasingly robust benchmarking methods requires that evaluation libraries remain flexible to new datasets and metrics. Finally, there remains a gap in synthesizing evaluations in order to deliver actionable takeaways about model performance. To enable unified, flexible, and actionable evaluations, we introduce EvalGIM (pronounced ''EvalGym''), a library for evaluating generative image models. EvalGIM contains broad support for datasets and metrics used to measure quality, diversity, and consistency of text-to-image generative models. In addition, EvalGIM is designed with flexibility for user customization as a top priority and contains a structure that allows plug-and-play additions of new datasets and metrics. To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions. The Evaluation Exercises contain easy-to-use and reproducible implementations of two state-of-the-art evaluation methods of text-to-image generative models: consistency-diversity-realism Pareto Fronts and disaggregated measurements of performance disparities across groups. EvalGIM also contains Evaluation Exercises that introduce two new analysis methods for text-to-image generative models: robustness analyses of model rankings and balanced evaluations across different prompt styles. We encourage text-to-image model exploration with EvalGIM and invite contributions at https://github.com/facebookresearch/EvalGIM/.
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall
Oscar Mañas
Reyhane Askari
Mark Ibrahim
Candace Ross
Pietro Astolfi
Tariq Berrada
Marton Havasi
Yohann Benchetrit
Karen Ullrich
Carolina Braga
Abhishek Charnalia
Maeve Ryan
Michael Rabbat
Michal Drozdzal
Jakob Verbeek
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. Ho… (see more)wever, while metrics and datasets abound, there are few unified benchmarking libraries that provide a framework for performing evaluations across many datasets and metrics. Furthermore, the rapid introduction of increasingly robust benchmarking methods requires that evaluation libraries remain flexible to new datasets and metrics. Finally, there remains a gap in synthesizing evaluations in order to deliver actionable takeaways about model performance. To enable unified, flexible, and actionable evaluations, we introduce EvalGIM (pronounced ''EvalGym''), a library for evaluating generative image models. EvalGIM contains broad support for datasets and metrics used to measure quality, diversity, and consistency of text-to-image generative models. In addition, EvalGIM is designed with flexibility for user customization as a top priority and contains a structure that allows plug-and-play additions of new datasets and metrics. To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions. The Evaluation Exercises contain easy-to-use and reproducible implementations of two state-of-the-art evaluation methods of text-to-image generative models: consistency-diversity-realism Pareto Fronts and disaggregated measurements of performance disparities across groups. EvalGIM also contains Evaluation Exercises that introduce two new analysis methods for text-to-image generative models: robustness analyses of model rankings and balanced evaluations across different prompt styles. We encourage text-to-image model exploration with EvalGIM and invite contributions at https://github.com/facebookresearch/EvalGIM/.
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall
Oscar Mañas
Reyhane Askari Hemmat
Mark Ibrahim
Candace Ross
Pietro Astolfi
Tariq Berrada
Marton Havasi
Yohann Benchetrit
Karen Ullrich
Carolina Braga
Abhishek Charnalia
Maeve Ryan
Michal Drozdzal
Jakob Verbeek
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. Ho… (see more)wever, while metrics and datasets abound, there are few unified benchmarking libraries that provide a framework for performing evaluations across many datasets and metrics. Furthermore, the rapid introduction of increasingly robust benchmarking methods requires that evaluation libraries remain flexible to new datasets and metrics. Finally, there remains a gap in synthesizing evaluations in order to deliver actionable takeaways about model performance. To enable unified, flexible, and actionable evaluations, we introduce EvalGIM (pronounced ''EvalGym''), a library for evaluating generative image models. EvalGIM contains broad support for datasets and metrics used to measure quality, diversity, and consistency of text-to-image generative models. In addition, EvalGIM is designed with flexibility for user customization as a top priority and contains a structure that allows plug-and-play additions of new datasets and metrics. To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions. The Evaluation Exercises contain easy-to-use and reproducible implementations of two state-of-the-art evaluation methods of text-to-image generative models: consistency-diversity-realism Pareto Fronts and disaggregated measurements of performance disparities across groups. EvalGIM also contains Evaluation Exercises that introduce two new analysis methods for text-to-image generative models: robustness analyses of model rankings and balanced evaluations across different prompt styles. We encourage text-to-image model exploration with EvalGIM and invite contributions at https://github.com/facebookresearch/EvalGIM/.
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall
Oscar Mañas
Reyhane Askari
Mark Ibrahim
Candace Ross
Pietro Astolfi
Tariq Berrada
Marton Havasi
Yohann Benchetrit
Karen Ullrich
Carolina Braga
Abhishek Charnalia
Maeve Ryan
Michael Rabbat
Michal Drozdzal
Jakob Verbeek
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. Ho… (see more)wever, while metrics and datasets abound, there are few unified benchmarking libraries that provide a framework for performing evaluations across many datasets and metrics. Furthermore, the rapid introduction of increasingly robust benchmarking methods requires that evaluation libraries remain flexible to new datasets and metrics. Finally, there remains a gap in synthesizing evaluations in order to deliver actionable takeaways about model performance. To enable unified, flexible, and actionable evaluations, we introduce EvalGIM (pronounced ''EvalGym''), a library for evaluating generative image models. EvalGIM contains broad support for datasets and metrics used to measure quality, diversity, and consistency of text-to-image generative models. In addition, EvalGIM is designed with flexibility for user customization as a top priority and contains a structure that allows plug-and-play additions of new datasets and metrics. To enable actionable evaluation insights, we introduce ''Evaluation Exercises'' that highlight takeaways for specific evaluation questions. The Evaluation Exercises contain easy-to-use and reproducible implementations of two state-of-the-art evaluation methods of text-to-image generative models: consistency-diversity-realism Pareto Fronts and disaggregated measurements of performance disparities across groups. EvalGIM also contains Evaluation Exercises that introduce two new analysis methods for text-to-image generative models: robustness analyses of model rankings and balanced evaluations across different prompt styles. We encourage text-to-image model exploration with EvalGIM and invite contributions at https://github.com/facebookresearch/EvalGIM/.
Improving Text-to-Image Consistency via Automatic Prompt Optimization
Oscar Mañas
Pietro Astolfi
Melissa Hall
Candace Ross
Jack Urbanek
Adina Williams
Michal Drozdzal
Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
Reyhane Askari Hemmat
Melissa Hall
Alicia Sun
Candace Ross
Michal Drozdzal
Boosting Latent Diffusion with Perceptual Objectives
Tariq Berrada
Pietro Astolfi
Jakob Verbeek
Melissa Hall
Marton Havasi
Michal Drozdzal
Yohann Benchetrit
Karteek Alahari
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the laten… (see more)t space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder. While this approach allows for efficient model training and sampling, it induces a disconnect between the training of the diffusion model and the decoder, resulting in a loss of detail in the generated images. To remediate this disconnect, we propose to leverage the internal features of the decoder to define a latent perceptual loss (LPL). This loss encourages the models to create sharper and more realistic images. Our loss can be seamlessly integrated with common autoencoders used in latent diffusion models, and can be applied to different generative modeling paradigms such as DDPM with epsilon and velocity prediction, as well as flow matching. Extensive experiments with models trained on three datasets at 256 and 512 resolution show improved quantitative -- with boosts between 6% and 20% in FID -- and qualitative results when using our perceptual loss.
Boosting Latent Diffusion with Perceptual Objectives
Tariq Berrada
Pietro Astolfi
Jakob Verbeek
Melissa Hall
Marton Havasi
Michal Drozdzal
Yohann Benchetrit
Karteek Alahari
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the laten… (see more)t space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder. While this approach allows for efficient model training and sampling, it induces a disconnect between the training of the diffusion model and the decoder, resulting in a loss of detail in the generated images. To remediate this disconnect, we propose to leverage the internal features of the decoder to define a latent perceptual loss (LPL). This loss encourages the models to create sharper and more realistic images. Our loss can be seamlessly integrated with common autoencoders used in latent diffusion models, and can be applied to different generative modeling paradigms such as DDPM with epsilon and velocity prediction, as well as flow matching. Extensive experiments with models trained on three datasets at 256 and 512 resolution show improved quantitative -- with boosts between 6% and 20% in FID -- and qualitative results when using our perceptual loss.
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Tariq Berrada
Pietro Astolfi
Melissa Hall
Reyhane Askari Hemmat
Yohann Benchetrit
Marton Havasi
Matthew J. Muckley
Karteek Alahari
Jakob Verbeek
Michal Drozdzal
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of… (see more) the best performing LDM training recipes are oftentimes not available to the research community, preventing apple-to-apple comparisons and hindering the validation of progress in the field. In this work, we perform an in-depth study of LDM training recipes focusing on the performance of models and their training efficiency. To ensure apple-to-apple comparisons, we re-implement five previously published models with their corresponding recipes. Through our study, we explore the effects of (i)~the mechanisms used to condition the generative model on semantic information (e.g., text prompt) and control metadata (e.g., crop size, random flip flag, etc.) on the model performance, and (ii)~the transfer of the representations learned on smaller and lower-resolution datasets to larger ones on the training efficiency and model performance. We then propose a novel conditioning mechanism that disentangles semantic and control metadata conditionings and sets a new state-of-the-art in class-conditional generation on the ImageNet-1k dataset -- with FID improvements of 7% on 256 and 8% on 512 resolutions -- as well as text-to-image generation on the CC12M dataset -- with FID improvements of 8% on 256 and 23% on 512 resolution.