Leibniz University Hannover is a renowned German research university with a focus on engineering, physics, and geospatial sciences. It is a member of the TU9 alliance, a consortium of leading technical universities in Germany. NEC Labs America partners with Leibniz University Hannover to study spatiotemporal learning, semantic segmentation, and urban-scale perception. Please read about our latest news and collaborative publications with Leibniz University Hannover.

Posts

Attribute-Centric Compositional Text-to-Image Generation

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