J. P. Lewis — accepted AI-conference papers

2024

Directed Diffusion: Direct Control of Object Placement through Attention Guidance

Wan-Duo Kurt Ma, Avisek Lahiri, J. P. Lewis, Thomas Leung, W. Bastiaan Kleijn

AAAI 2024technical

Text-guided diffusion models such as DALLE-2, Imagen, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images are of very high quality. However, these models often struggle to com…

Cited by 59 Source ↗PDF ↗code ↗Scholar ↗

2017

The Shattered Gradients Problem: If resnets are the answer, then what is the question?

David Balduzzi, Marcus Frean, Lennox Leary, J. P. Lewis, Kurt Wan-Duo Ma, Brian McWilliams

ICML 2017poster

A long-standing obstacle to progress in deep learning is the problem of vanishing and exploding gradients. Although, the problem has largely been overcome via carefully constructed initializations and batch normalization, architectures incorporating skip-connections such as highway and resnets perfo…

Cited by 527 Source ↗PDF ↗code ↗Scholar ↗