activity
20162024
most citedThe Importance of Skip Connections in Biomedical Image Segmentation

112 citations · 148 across the 10 of their papers we have counts for

collaborators

11 papers

cs.CV2024

EvalGIM: A Library for Evaluating Generative Image Models

Melissa Hall, Oscar Mañas, Reyhane Askari-Hemmat +14

As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. However, while metrics and datasets abound…

cs.CV2024

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

Reyhane Askari Hemmat, Melissa Hall, Alicia Sun +3

With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases. Recent work has found that state-of-the-art…

cs.CV20243 cited

Consistency-diversity-realism Pareto fronts of conditional image generative models

Pietro Astolfi, Marlene Careil, Melissa Hall +5

Building world models that accurately and comprehensively represent the real world is the utmost aspiration for conditional image generative models as it would enable their use as…

cs.CV20246 cited

Improving Text-to-Image Consistency via Automatic Prompt Optimization

Oscar Mañas, Pietro Astolfi, Melissa Hall +6

Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic im…

cs.RO20242 cited

InCoRo: In-Context Learning for Robotics Control with Feedback Loops

Jiaqiang Ye Zhu, Carla Gomez Cano, David Vazquez Bermudez +1

One of the challenges in robotics is to enable robotic units with the reasoning capability that would be robust enough to execute complex tasks in dynamic environments. Recent adva…

cs.CV20231 cited

Controllable Image Generation via Collage Representations

Arantxa Casanova, Marlène Careil, Adriana Romero-Soriano +3

Recent advances in conditional generative image models have enabled impressive results. On the one hand, text-based conditional models have achieved remarkable generation quality,…