The University of Bath is a public research university in Bath, England, which received its royal charter in 1966. Tracing its roots back to 1595, it is known for its high rankings in overall performance, student satisfaction, and graduate employability, with a global outlook and a focus on impactful research. We have collaborated with the University of Bath on machine learning systems that improve image synthesis and interpretation. Our research has focused on enhancing the stability of generative models and improving the disentanglement of representations in deep neural networks. Please read about our latest news and collaborative publications with the University of Bath.

Posts

Attribute-Centric Compositional Text-to-Image Generation

/in /by

Despite the recent impressive breakthroughs in text-to-image generation, generative models have difficulty in capturing thedata distribution of underrepresented attribute compositions while over-memorizing overrepresented attribute compositions,which raises public concerns about their robustness and fairness. To tackle this challenge, we propose ACTIG, an attributecentriccompositional text-to-image generation framework. We present an attribute-centric feature augmentation and a novelimage-free training scheme, which greatly improves model’s ability to generate images with underrepresented attributes.Wefurther propose an attribute-centric contrastive loss to avoid overfitting to overrepresented attribute compositions.We validateour framework on the CelebA-HQ and CUB datasets. Extensive experiments show that the compositional generalization ofACTIG is outstanding, and our framework outperforms previous works in terms of image quality and text-image consistency

Read more