Search Results for author: Adriana Romero-Soriano

Found 20 papers, 12 papers with code

Decomposed evaluations of geographic disparities in text-to-image models

no code implementations17 Jun 2024 Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa, Oindrila Saha, Adina Williams, Adriana Romero-Soriano, Megan Richards, Polina Kirichenko, Melissa Hall

Recent work has identified substantial disparities in generated images of different geographic regions, including stereotypical depictions of everyday objects like houses and cars.

Attribute Diversity +1

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance

no code implementations6 Jun 2024 Reyhane Askari Hemmat, Melissa Hall, Alicia Sun, Candace Ross, Michal Drozdzal, Adriana Romero-Soriano

With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases.


Improving Text-to-Image Consistency via Automatic Prompt Optimization

no code implementations26 Mar 2024 Oscar Mañas, Pietro Astolfi, Melissa Hall, Candace Ross, Jack Urbanek, Adina Williams, Aishwarya Agrawal, Adriana Romero-Soriano, Michal Drozdzal

In this paper, we address these challenges and introduce a T2I optimization-by-prompting framework, OPT2I, which leverages a large language model (LLM) to improve prompt-image consistency in T2I models.

Language Modelling Large Language Model

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning

1 code implementation21 Mar 2024 Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero-Soriano, Kamalika Chaudhuri, Mike Rabbat, Chuan Guo

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable.

Memorization Retrieval

Feedback-guided Data Synthesis for Imbalanced Classification

no code implementations29 Sep 2023 Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano

In this work, we introduce a framework for augmenting static datasets with useful synthetic samples, which leverages one-shot feedback from the classifier to drive the sampling of the generative model.

Classification imbalanced classification

Graph Inductive Biases in Transformers without Message Passing

1 code implementation27 May 2023 Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim

Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings.

Graph Classification Graph Regression +2

Improved baselines for vision-language pre-training

1 code implementation15 May 2023 Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano, Jakob Verbeek, Michal Drozdzal

Indeed, we find that a simple CLIP baseline can also be improved substantially, up to a 25% relative improvement on downstream zero-shot tasks, by using well-known training techniques that are popular in other subfields.

Contrastive Learning Data Augmentation +1

Controllable Image Generation via Collage Representations

no code implementations26 Apr 2023 Arantxa Casanova, Marlène Careil, Adriana Romero-Soriano, Christopher J. Pal, Jakob Verbeek, Michal Drozdzal

Our experiments on the OI dataset show that M&Ms outperforms baselines in terms of fine-grained scene controllability while being very competitive in terms of image quality and sample diversity.

Attribute Image Generation

Instance-Conditioned GAN Data Augmentation for Representation Learning

no code implementations16 Mar 2023 Pietro Astolfi, Arantxa Casanova, Jakob Verbeek, Pascal Vincent, Adriana Romero-Soriano, Michal Drozdzal

We showcase the benefits of DA_IC-GAN by plugging it out-of-the-box into the supervised training of ResNets and DeiT models on the ImageNet dataset, and achieving accuracy boosts up to between 1%p and 2%p with the highest capacity models.

Data Augmentation Few-Shot Learning +1

Learning to Substitute Ingredients in Recipes

1 code implementation15 Feb 2023 Bahare Fatemi, Quentin Duval, Rohit Girdhar, Michal Drozdzal, Adriana Romero-Soriano

Recipe personalization through ingredient substitution has the potential to help people meet their dietary needs and preferences, avoid potential allergens, and ease culinary exploration in everyone's kitchen.

Recipe Generation

Uncertainty-Driven Active Vision for Implicit Scene Reconstruction

1 code implementation3 Oct 2022 Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai, David Meger, Adriana Romero-Soriano

We evaluate our proposed approach on the ABC dataset and the in the wild CO3D dataset, and show that: (1) we are able to obtain high quality state-of-the-art occupancy reconstructions; (2) our perspective conditioned uncertainty definition is effective to drive improvements in next best view selection and outperforms strong baseline approaches; and (3) we can further improve shape understanding by performing a gradient-based search on the view selection candidates.

Scene Understanding

Revisiting Hotels-50K and Hotel-ID

1 code implementation20 Jul 2022 Aarash Feizi, Arantxa Casanova, Adriana Romero-Soriano, Reihaneh Rabbany

In this paper, we propose revisited versions for two recent hotel recognition datasets: Hotels50K and Hotel-ID.

Image Retrieval Retrieval

On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction

1 code implementation30 Mar 2022 Tim Bakker, Matthew Muckley, Adriana Romero-Soriano, Michal Drozdzal, Luis Pineda

Most current approaches to undersampled multi-coil MRI reconstruction focus on learning the reconstruction model for a fixed, equidistant acquisition trajectory.

MRI Reconstruction SSIM

Parameter Prediction for Unseen Deep Architectures

1 code implementation NeurIPS 2021 Boris Knyazev, Michal Drozdzal, Graham W. Taylor, Adriana Romero-Soriano

We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet.

Parameter Prediction

Graph Attention Networks with Positional Embeddings

no code implementations9 May 2021 Liheng Ma, Reihaneh Rabbany, Adriana Romero-Soriano

In this framework, the positional embeddings are learned by a model predictive of the graph context, plugged into an enhanced GAT architecture, which is able to leverage both the positional and content information of each node.

Graph Attention Node Classification +1

Generating unseen complex scenes: are we there yet?

no code implementations7 Dec 2020 Arantxa Casanova, Michal Drozdzal, Adriana Romero-Soriano

In this paper, we propose a methodology to compare complex scene conditional generation models, and provide an in-depth analysis that assesses the ability of each model to (1) fit the training distribution and hence perform well on seen conditionings, (2) to generalize to unseen conditionings composed of seen object combinations, and (3) generalize to unseen conditionings composed of unseen object combinations.


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